Adversarial Transferability

Unsupervised domain adaptation (UDA) for semantic segmentation remains challenging under adverse weather conditions because severe appearance changes enlarge the domain gap and degrade the reliability of pseudo labels in the target domain. To address this problem, we propose an Intra-Class Mixing Consistency (ICM) framework that enforces prediction consistency between an intra-class mixed image and its original counterpart. Unlike previous mixing-based consistency methods that combine regions across different images or domains and may introduce unrealistic semantic inconsistencies, ICM performs mixing within the same image and semantic class, preserving realistic semantic layout for consistency regularization. With ICM, we establish a new state-of-the-art performance for clear-to-adverse-weather unsupervised domain adaptation (UDA) in semantic segmentation. On the Cityscapes $\rightarrow$ ACDC benchmark, our method achieves 75.7% mIoU, outperforming the previous state of the art by +1.9 pp, demonstrating its effectiveness in mitigating class confusion under challenging environmental conditions. The code is provided in the supplementary material.

Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibility shapes attack success remains poorly understood. Prior studies evaluate limited detector pools and rarely disentangle architectural from training factors. We conduct a controlled evaluation of adversarial transferability across 60 detectors spanning six backbones, two pretraining regimes, and five training-data configurations, using two attack procedures: AutoAttack (AA) and the Carlini--Wagner attack with Expectation over Transformation (CW--EOT). Matched comparisons reveal significantly higher transfer when source and target share an exact backbone, architecture family, pretraining regime, or training data. This compatibility structure is attack-dependent: exact backbone compatibility has the largest effect under AA, whereas shared pretraining and training data have the largest effects under CW--EOT. When transfer is averaged across non-target sources, mean attack success rate (ASR) is $7.21\%$ under AA and $19.52\%$ under CW--EOT. By contrast, a multi-source oracle combining both attacks attains a $64.48\%$ mean ASR after excluding exact backbone and training-data matches, showing that source averaging can substantially understate target vulnerability. We release 240,000 adversarially perturbed images, complete pairwise transfer results, detector configurations, and evaluation code. These findings establish source--target compatibility and source-model selection as central dimensions of credible transfer-based black-box robustness evaluation.

Attributes describing data content and context can induce diverse imbalance patterns that go beyond label imbalance alone. However, existing studies primarily address label imbalance while overlooking data attributes, such as topics and demographics, which can induce meaningful subgroup structure while causing model degradation on underrepresented subgroups. We propose Attribute-Agnostic Imbalance Augmentation (AIA$^{2}$), a framework for improving model robustness under varying subgroup imbalances without explicit subgroup annotations. AIA$^{2}$ automatically discovers varying imbalances via latent semantic distributions, obtains slices with both learning difficulty and subgroup imbalance deficits, and deploys a large language model (LLM) for subgroup-aware imbalance augmentation. We have evaluated AIA$^{2}$ on 5 popular corpora with rich domains and their attribute values, covering social issues and diverse topics. Results show improved performance on the lowest-performing subgroups and consistent gains over competitive baselines. Ablation studies confirm complementary contributions from each component, and additional analyses show that AIA$^{2}$ provides a practical and consistent way to improve worst-group robustness under data subgroup imbalance. Code is available at https://github.com/trust-nlp/AIA2-Subgroup-Robustness.

Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models. Beyond perturbation generation, transferability is fundamentally governed by the coupling of initialization, surrogate adaptation, and gradient dynamics. We revisit this challenge from a bilevel-minimax perspective and propose BMAT (Bilevel-Minimax Adversarial Transfer). The bilevel formulation captures the dependency between initialization and perturbation, while the inner minimax problem promotes surrogate robustness for cross-architecture generalization. Algorithmically, we develop an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization. We further provide theoretical insights into the optimization dynamics of the proposed bilevel-minimax framework. Extensive experiments on classification and segmentation benchmarks show that BMAT outperforms more than 10 strong baselines across more than 30 victim models, improving both intra- and cross-architecture transfer and yielding up to a 2x reduction in mIoU. Code is available at https://github.com/callous-youth/BMAT.

In this paper, we extend a weak adversary neural network pushforward method for solving time dependent Boltzmann equation and a weak formulation of the collision operator is proposed where an invertible neural pushforward mapping is used to generating samples given by the distribution governed by the Boltzmann equation. The training of the pushforward mapping is learnt by enforcing the weak form of the Boltzmann equation. Numerical results have demonstrated the effectiveness of the proposed method.

Millimeter-wave human activity recognition suffers significant performance degradation when the user's orientation changes relative to the sensing system, yet collecting labeled multi-orientation data is labor-intensive and costly. To eliminate the need for exhaustive multi-orientation measured data, we develop a physics-guided simulator that synthesizes orientation-diverse wireless training data from single-orientation motion. Specifically, to suppress orientation-induced feature variations, we propose a dual-attention network that extracts activity-discriminative and orientation-robust representations from dual-link Doppler spectrograms. To bridge the simulation-to-reality gap, we introduce an adversarial unsupervised transfer learning mechanism that aligns feature distributions using only a small number of unlabeled target-domain samples. The S2M-Sense platform shows high fidelity in reproducing real-world signatures, validated against 60.48 GHz mmWave measured data with an average structural similarity index measure (SSIM) of 0.84 between simulated and measured Doppler spectrograms across all 4 activities and 4 orientations. Experimental results show that S2M-Sense achieves 88.33% recognition accuracy using only the dual-link multi-orientation simulated dataset, which improves to 95% after simulation-to-reality transfer learning with as few as 16 unlabeled measured samples. Both cases with and without transfer learning outperform state-of-the-art cross-domain sensing methods.

Real-time object detectors achieve remarkable accuracy under controlled conditions, yet degrade sharply on non-ideal inputs: fisheye distortion, game-renderedcharacters, aerial viewpoints, and 360°panoramas. We present YOLOv14, a detection framework with four adaptive mechanisms designed for specific types of inputvariation:(1) Deformable Area-Attention with windowed computation and shiftedwindows for geometric distortion;(2) Multi-level Game2Real Alignment with progressive adversarial training for domain shift;(3) View-Aware Contrastive Learning with adaptive temperature for viewpoint invariance; and (4) Scene-Adaptive Augmentation with dynamic loss balancing for scene diversity. Together, YOLOv14 achieves 49.1 mAP on COCO val2017 at 2.91 ms (T4 GPU), and delivers substantial gains on fisheye (+4.1 mAP), panorama (+6.6 mAP), drone (+6.4 mAP), andour synthesized game-character benchmark (+26.1 mAP). We release code and models to facilitate reproducible research.

Sharpness-Aware Minimization (SAM) improves generalization by seeking parameters whose loss is robust to local adversarial perturbations, but the quantitative mechanism underlying its implicit bias toward flat minima remains unclear. In particular, the perturbation radius $ρ$ is typically treated as an isolated tuning parameter, despite defining the neighborhood in which SAM measures sharpness. We analyze mini-batch SAM near an interpolating minimum through linear stability. Under local linearization and gradient-noise alignment assumptions, we prove that every linearly stable minimum satisfies $λ_{\max}\leq\sqrt[3]{bΓ/(2ρη^2)}$, where $λ_{\max}$ is the largest Hessian eigenvalue, $b$ is the batch size, $η$ is the learning rate, and $Γ$ bounds the gradient norm. The bound quantitatively characterizes SAM's implicit flatness bias: holding the other quantities fixed, a smaller batch size, a larger learning rate, or a larger radius restricts linearly stable SAM to flatter minima. It also exposes a necessary trade-off: $ρ$ should be large enough to promote flatness, yet remain local enough to preserve the approximation and stable training. We validate this prediction in a controlled study of 900 models on CIFAR-100 with ResNet-18 and VGG-19, where increasing $ρ$ is consistently associated with a smaller largest Hessian eigenvalue across batch-size and learning-rate settings. Finally, we instantiate the analysis in Taylor-Locality Controlled SAM (TLC-SAM), which adjusts $ρ$ using the observed Taylor-approximation error and further reduces the top Hessian eigenvalue relative to fixed-radius SAM. Our results provide quantitative hyperparameter bounds and a stability--locality perspective for analyzing and designing SAM variants.

Vision-language models (VLMs) exhibit strong generalization across multimodal tasks but remain vulnerable to adversarial perturbations. Existing attacks typically follow single-trajectory gradient optimization or task-specific objectives, limiting search-space exploration and cross-task transferability. We propose an evolutionary-computation-guided cross-modal attack framework for unified VLMs. The framework adaptively searches both textual and visual spaces. On the textual side, it evolves hard negative semantic embeddings around the source-category representation to provide diverse cross-modal repulsion. On the visual side, it maintains a population of object-region perturbations and combines momentum-based gradient updates with evolutionary selection, mutation, and crossover to more reliably explore multiple feasible trajectories. Jointly optimizing semantic negative guidance and localized perturbations generates adversarial examples that consistently shift source-object semantics toward target categories across vision-language tasks. Theoretical analyses show that the co-evolutionary search preserves perturbation feasibility, prevents degradation of the best observed fitness, and increases the probability of reaching high-margin adversarial regions compared with single-trajectory optimization. Experiments on Florence-2, OFA, and UnifiedIO-2 demonstrate strong overall attack performance across image captioning, object detection, region categorization, and object localization. Ablation studies further verify the complementary effectiveness of text-side semantic evolution and image-side perturbation evolution, as well as the framework's efficiency and cross-task transferability.

Adversarial training is one of the most effective defenses against adversarial attacks, yet the computational cost remains prohibitive at modern scales, especially for large language models (LLMs). While existing mitigation strategies, e.g., latent adversarial training (LAT), have been developed, they still incur a high computational cost. In this work, we comprehensively investigate computation-efficient strategies to speed up LAT from two complementary perspectives: (1) Defense-side optimization: We explore the representation fine-tuning (ReFT) within LAT, and reveal a potential issue if there is a mismatch on which tokens to apply ReFT and the attack. (2) Attack-side optimization: When computing adversarial attacks in each LAT iteration, we extract only the relevant circuits from the LLM to construct a lightweight surrogate model, avoiding the computation in the forward-backward passes through the full model during the attack generation. For both perspectives, we provide theoretical justifications and numerical evidence to illustrate the effectiveness of the proposed strategies. Ultimately, compared to standard LAT with full fine-tuning, our method on average reduces per-step adversarial-training FLOPs by 48.1% while requiring only 0.0118% trainable parameters.

Pre-trained language models have significantly improved sentence representation learning, yet their embedding remain sensitive to semantic preserving textual perturbations such as synonym substitution, masking and word dropout. This work proposes a lightweight Contrastive Denoising Autoencoder (CDAE) that refines pre-trained BERT embedding by jointly optimizing contrastive and reconstruction objective to learn perturbation-invariant representation. We evaluate the proposed framework using multiple perturbation strategies with varying strengths and compare it against the original BERT embeddings and SimCSE. Experimental results show that CDAE consistently preserves higher embedding similarity under perturbations, with the improvements becoming more pronounced as framework effectively enhances representation stability while preserving semantic information, highlighting perturbation-invariant learning as a promising direction for improving sentence embeddings. The source code is publicly available at: https://github.com/ComputationIASBS/CDAE

Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency. We study this trade-off in kernel regression over a reproducing kernel Hilbert space (RKHS). It is shown that, under squared loss, adversarial training in RKHS introduces a term involving the product of the function norm with the mean absolute value of the response noise, which we call the \textit{noise premium}. Our analysis shows that the noise premium makes the prediction error of adversarial training converge strictly more slowly than the nonparametric minimax benchmark even after balancing approximation and estimation errors. Moreover, for a fixed perturbation budget, once the budget exceeds a certain threshold, the solution to adversarial training collapses to the zero function. To mitigate these effects of the noise premium, we propose noise-debiased adversarial training. The resulting noise-debiased estimator can attain the minimax optimal rate up to a logarithmic factor for the prediction error, raises the collapse threshold, and admits an explicit bound on the increase in adversarial loss. Numerical experiments on synthetic and real data support the theoretical findings and validate the effectiveness of the proposed noise-debiased method.

Deep neural networks (DNNs) have achieved remarkable success in classical machine learning problems. However, they are known to be vulnerable to adversarial attacks. Countermeasures proposed in the literature, notably Information Bottleneck Distillation (IBD) introduced by Kuang et al., degrade the classification accuracy on clean inputs while improving the robustness to adversarial inputs. In this work, we extend the IBD framework by introducing an extra teacher model (clean teacher) trained with only clean inputs, into the distillation process from a robust teacher model trained by adversarial training. The features of both clean and robust teachers are transferred to the student through a cross-layer attention matrix. Experimental results on the CIFAR-10 and CIFAR-100 datasets show that the proposed method improves classification accuracy on clean samples compared to the original IBD, while maintaining similar accuracy on adversarial samples. Furthermore, our methods are competitive with state-of-the-art approaches, including the recent dual-teacher distillation framework B-MTARD, particularly in terms of the harmonic mean between clean and robust accuracy. We also analyze the impact of different training settings that have different influences on the attention module.

Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbreviated PAoI) to stay below a hard per-slot deadline, not merely an average bound. Existing approaches meet this requirement only under restrictive assumptions: stochastic channels for Whittle-index AoI, simulator rollouts for deep reinforcement learning, or sublinear cumulative violation for long-term constrained online convex optimization. Under adversarial coefficients, OCO-PAoI-Hard guarantees zero per-slot violation of the modeled AoI state under one-step viability and O(sqrt(T)) regret against any static safe comparator; packet-level safety requires stronger service assumptions. Our key observation is that the fractional peak-AoI deadline collapses exactly to an affine half-space constraint on the resource-allocation vector, turning hard real-time scheduling into time-varying constrained online convex optimization over a polyhedral safe set. A strictly causal proposal-shield-update loop enforces feasibility through one Euclidean projection per slot, the gradient step preserves no-regret behavior, and the classical virtual queue is reduced to an a-posteriori certificate. We establish closed-form static and dynamic regret bounds, a matching Omega(sqrt(T)) minimax lower bound, a margin-safe variant against execution noise, and a deadline-induced competitive ratio. On a four-sensor adversarial fluid-model trap channel, OCO-PAoI-Hard attains zero modeled-state deadline violations across all ten seeds, while four representative baselines miss between 1.65 percent and 64.0 percent of slots, and the empirical normalized regret stays below the theoretical envelope across two orders of magnitude in T.

Semantic segmentation models are vulnerable to transferable adversarial perturbations, yet evaluating transfer attacks on dense prediction models can be computationally expensive. Existing ensemble attacks often rely on multiple surrogate models, increasing the computation cost, even harder for segmentation. This paper studies an efficient single-source alternative for transferable attacks on semantic segmentation. We formulate transferable attack composition as a chained computation over differentiable attack components, allowing the expensive source-model gradient computation to be shared. To reduce the update instability introduced by chained composition, we further use an integrated-gradient-style path-averaged direction as an empirical stabilization heuristic. Experiments on Pascal VOC and Cityscapes evaluate the resulting transferability efficiency trade-off across CNN- and transformer-based segmentation models. IGME achieves competitive transferability compared with single-source baselines and favorable runtime compared with model-ensemble attacks, while requiring access to only one source model.

Ultraconstructive Model Theory (UCMT) replaces idealized satisfaction, at finite compu- tational scale, by bounded adversarial survival. A finite partial structure is tested by an Opponent (Devil) drawing legal challenges from a bounded attack surface, repaired by a Builder (God) through legal replies, and certified by a symbolic Judge

Automatic depression detection with deep learning has shown promise but often suffers from limited generalization due to domain shift arising from inter-speaker variability. To address this critical issue, we present the first patient-independent multimodal depression detection framework that incorporates domain generalization (DG), jointly leveraging both acoustic and textual modalities. The proposed model integrates bidirectional Long Short-Term Memory (BiLSTM) with intra- and cross-modal attention mechanisms, accompanied by segment-level fusion for decision-making. Generalization is further enhanced by applying a gradient reversal layer inspired by Domain-Adversarial Training of Neural Networks (DANN), which promotes domain-invariant representations by adversarially limiting the model's ability to identify individual speakers, effectively reducing patient-specific bias. Conducting experiments on the Androids-Corpus dataset with a 5-fold cross-validation (CV) protocol, various pairings of audio and text feature extractors were evaluated over different segment durations, determining MelSpec and ItalianBERT as the optimal baseline at a 30-second segment duration. The addition of DG to this baseline yields a 2.5% increase in accuracy and 3.3% in F1-score, achieving 93.2% accuracy, 93.2% precision, 96.2% recall, and 94.2% F1-score, surpassing all existing benchmarks. Extensive ablation studies assess the impact of multimodal fusion, deep architectural choices, and DG, highlighting their combined contribution to robust and generalizable depression detection.

Metal artifacts generated by dental implants significantly degrade cone-beam computed tomography (CBCT) volumes, obscuring critical anatomical structures and compromising diagnostic precision. To address this, an unsupervised deep learning framework has been proposed for Metal Artifact Reduction (MAR) utilizing a Cycle-Consistent Adversarial Network (CycleGAN) optimized for high-fidelity restoration. Unlike supervised methods that rely on unattainable voxel-aligned paired datasets, the proposed approach leverages an unpaired dataset of approximately 4,000 images, curated from the public ToothFairy dataset. The architecture integrates U-Net-based generators and PatchGAN discriminators, specifically tuned to mitigate generative hallucinations and preserve morphological integrity. Quantitative benchmarking on a held-out test set demonstrates a 34.6% improvement in the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score, a substantial reduction in Fréchet Inception Distance (FID) from 207.03 to 157.04, and a superior Structural Similarity Index Measure (SSIM) of 0.9105. The framework achieves real-time efficiency with a 3.03 ms inference time per slice, effectively suppressing artifacts while preserving anatomical detail. Expert validation confirms high fidelity; however, to ensure reliability in extreme cases, the architecture is recommended as a clinical decision-support tool under human-in-the-loop oversight. By enhancing diagnostic clarity via a scalable software pipeline, this study provides a robust solution for high-fidelity dental implant imaging.

Supervised learning models in the predictive maintenance field are regularly trained on highly imbalanced industrial datasets: machine failures occur rarely but have a disproportionate effect on operations. In addition to the clear class disparity, failure data are typically non-homogeneous, with different failure modes arising from distinct physical processes and exhibiting a multimodal distribution across minorities and classes. Traditional imbalance-management methods, e.g., undersampling, SMOTE-based interpolation, or cost-sensitive learning, typically assume that the minority population is homogeneous. This means their effectiveness is severely limited in the multifaceted conditions encountered in industrial practice. This paper determines the possibility of a failure-type-conscious generative augmentation program to improve the identification of infrequent failures in predictive maintenance systems. An experimental design that is leakage-safe is used to compare five imbalance-handling methods: cost-sensitive learning, random undersampling, SMOTE oversampling, single-generator GAN augmentation, and a specialized multi-generator GAN architecture that has independent generators that are asked to learn individual failure subtypes. Precision/Recall-oriented measures are used to quantify model performance; the main evaluation measure is the PR-AUC. Experiments conducted on the AI4I 2020 predictive maintenance dataset indicate that the proposed multi-generator GAN framework produces more realistic minority samples, yielding higher PR-AUC and recall scores compared to traditional resampling methods and individual-generator GAN augmentation.

While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.g., zero-shot classification) and consequently lack generalizability across various multimodal tasks. To address this limitation, we propose a dual adversarial fine-tuning framework that jointly optimizes visual and semantic supervision signals from two modalities, enhancing model robustness while generalizing across multiple downstream tasks. The proposed framework comprises two core components, i.e., $\textbf{Visual}$ supervision branch and $\textbf{Semantic}$ supervision branch. The former branch leverages features from clean images, extracted via a frozen original vision encoder, to guide adversarial robustness while the latter incorporates caption-image alignment as a contextual signal to preserve semantic coherence under attack. Moreover, our method achieves cross-task robustness by simply replacing the CLIP vision encoder in the original model, with no need of separate task-specific retraining or architecture modifications.Extensive experiments demonstrate that our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering (VQA) tasks.

Flow-based models have established state-of-the-art performance in generative modeling across domains, but are hard to interpret due to their complex latent embeddings. In particular, the entanglement of generative factors in the latent space hinders controlled generation. We circumvent this issue by appealing to a novel conditional generator based on Lie groups that disentangles an alternative latent space, which is aligned closely with the latent flow space using an adversarial loss. Our approach facilitates interpretable conditional generation while obviating the need to expand the dimensionality of the flow space (owing to its invertibility requirements). The proposed model demonstrates strong performance across conditional image (including, outperforming StyleGAN on MNIST, dSprites) and molecule (using standard QM9, ZINC and MOSES) generation tasks

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot manipulation; however, their transition to real-world environments reveals vulnerabilities to minor environmental perturbations. We propose FLARE, an optimized physical spotlight attack framework that exploits these vulnerabilities via targeted illuminations, dropping baseline task success rates to zero without any access to model internals. While adversarial training is the standard countermeasure, we identify a critical and previously underestimated defensive pitfall: naive data augmentations incorrectly condition VLA models to discard color as noise, collapsing their visual perception into a purely shape-biased processor. We expose this degradation through a diagnostic grayscale evaluation, in which the defended model maintains high success rates on grayscale inputs, while its success rate on benign, color-dependent real-world tasks drops to at most 47.5%, well below the undefended baseline. To address this, we propose ChromaGuard, a chroma-preserving adversarial training method. On a physical 6-DoF robotic platform, we demonstrate that ChromaGuard achieves 97.5% and 92.5% success rates in benign and attacked color-dependent tasks, respectively.

Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations. Existing test-time adaptation methods typically rely on sample-level confidence heuristics, overlooking the intrinsic distributional structure of the data. This sample-centric approach limits robustness, as it fails to distinguish confident adversarial mispredictions from true semantic consistency. In this work, we observe that adversarial distortion is structurally brittle: while holistic representations are corrupted, semantic integrity is often preserved in the distribution of augmented views. Motivated by this insight, we propose RITA, a Robust test-tIme prompt-TAdaptation framework that shifts from sample-level estimates to distribution-level alignment. Specifically, RITA employs optimal transport to align the distribution of augmented visual features with textual prototypes, mitigating adversarial outliers and rectifying cross-modal semantic misalignment. Furthermore, we introduce a dynamic cache to progressively accumulate reliable cues from the test stream for online refinement. Extensive experiments demonstrate that RITA significantly improves adversarial robustness without compromising clean accuracy.

Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Latent Adversarial Training (LAT) is among the most effective defenses, but can degrade utility and requires training on large datasets of harmful prompts. We introduce Latent Personality Alignment (LPA), which replaces explicit harm refusal with adversarial training on just 66 harm-agnostic statements drawn from psychometric personality literature. We hypothesize that personality-anchored representations share latent structure with harm avoidance, so adversarially stabilizing them implicitly constrains the subspace exploited by jailbreak attacks. LPA achieves near-zero attack success rates on HarmBench across direct requests and five jailbreak methods, despite never seeing harmful content during training and no loss of performance on standard benchmarks. Moreover, the training process is lightweight; the entire procedure completes in minutes on a single GPU and uses 75x fewer examples than standard LAT. Extensive ablations demonstrate the robustness, efficiency, and generalization of our method.

Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow turbulence as the perturbation prior. A lightweight generator synthesizes a single input-agnostic perturbation regularized toward physically plausible airflow patterns. Optimized on one surrogate CLIP model, it attains a mean zero-shot scene-classification attack success rate (ASR, the fraction of samples whose top-1 class changes) of 48.5% across five diverse CLIP backbones, far exceeding four IR-specific physical baselines (27.7--37.0%). Applied to six state-of-the-art VLMs, it cuts scene-classification accuracy by up to 38.2% relative, yet paradoxically makes some models more confident in their IR analysis, confabulating the perturbation as genuine thermal evidence such as temperature gradients and convection. Ablations show the airflow prior raises physical plausibility at no measurable cost to attack success. Together with a benchmark spanning eleven models and four tasks, these findings expose critical vulnerabilities in the rapidly expanding IR VLM ecosystem.

Multi-perturbation adversarial training (MAT) aims to achieve robustness against multiple $\ell_p$ perturbations but suffers from robustness trade-offs between different threats. To address this, we employ a mixture of experts (MoE) to route different threats through distinct model pathways. However, naive application of MoE encounters two critical challenges: experts tend to overlook threat-specific features and redundantly capture features shared across threats, and gating networks suffer from threat-agnostic routing where they learn nearly identical routing patterns across threats, thus preventing the construction of threat-specific model pathways. To this end, we propose Robust Mixture of Low-Rank Experts (RoME), where each expert is a low-rank additive update to the shared backbone, allowing it to capture threat-common features while experts focus on threat-specific information. To address threat-agnostic routing, RoME introduces (i) dual-scale gating that exploits threat-discriminative signals from local and global level features, and (ii) threat-guided gating diversification that enforces diverse expert utilization across threats. Extensive experiments demonstrate that RoME outperforms existing state-of-the-art MAT in union robustness and natural accuracy and improves robustness against unseen threats. Codes are available at https://github.com/wkim97/RoME.

Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models. Since adversarial attacks and adversarial robustness are mathematically defined problems that can be optimised directly with end-to-end differentiable search, adversarial robustness is more widely applicable than other robustness metrics such as corruption and perturbation robustness, and new kinds of adversarial attacks are beneficial for robustness testing. Attacks are targeted or non-targeted depending on whether the image is modified to misclassify to a particular class or to any incorrect class; we focus on the non-targeted setting. Finding the optimal input data points and hyper-parameters for generating non-targeted adversarial attacks remains a challenge for current methods like the Fast Gradient Method, Basic Iterative Method and Virtual Adversarial Method. We propose a new method, the "Binary Iterative Method" (BinIM), which uses a divide-and-conquer paradigm to optimise parameters and hyper-parameters for the generation of non-targeted attacks. We compare our method to other gradient-based adversarial attacks evaluated over pre-trained networks (InceptionV3, InceptionV2, ResNet V2 152) on classification tasks. On 1000 randomly-sampled images from the standard ImageNet dataset, the Binary Iterative Method outperforms all other gradient-based methods, qualitatively making the classifier misclassify with confidence up to 0.995 while reducing the probability of the true label to 2.21e-09 (approximately 0).

Adversarial robustness in Unsupervised Domain Adaptation (UDA) remains a significant challenge due to noisy pseudo labels and inherent distributional shifts between the clean source and adversarially perturbed target domains. Existing approaches often fail to achieve an optimal trade-off between robustness and accuracy, as pseudo-labels generated by domain-adapted models tend to introduce classification errors under adversarial attacks. In this work, we propose \textbf{SFT+RL}, a two-stage robust UDA framework that integrates Supervised Fine Tuning (SFT) and Reinforcement Learning (RL) on top of CLIP's pre-trained visual encoder. In the SFT stage, we adversarially fine-tune a linear classifier using PGD-based perturbations over the labelled source domain while partially unfreezing CLIP's projection layer. It allows adaptation to adversarial noise while preserving CLIP's rich semantic priors. We introduce a confidence-guided pseudo-labeling strategy in the RL stage to annotate unlabeled target samples progressively. Pseudo labels are filtered using a decaying confidence threshold to balance quality and coverage, and the model is trained on a composite dataset formed by combining clean source samples with high-confidence target samples. Adversarial training is applied to mixed batches of clean and adversarial examples to enhance cross-domain robustness. Comprehensive evaluations on three benchmark datasets OfficeHome~\cite{tomm-ude}, PACS~\cite{pacs}, and VisDA~\cite{visda} demonstrate the effectiveness of our approach. Notably, \textbf{SFT+RL} achieves average improvements of \textbf{10.2%} in clean accuracy and \textbf{15.8%} in adversarial robustness across all three datasets, outperforming existing state-of-the-art methods.

Safety-critical applications require classifiers that are both robust and reliable. Adversarial training is a widely adopted defense for improving robustness in deep neural networks; however, its effect on the reliability of predictive uncertainty remains underexplored. We investigate this gap through the lens of selective classification, which has rarely been systematically analyzed alongside adversarial robustness. We introduce a unified benchmark for the robustness-uncertainty trade-off. It standardizes architectures, augmentations, threat models, and evaluation metrics across clean, adversarial, and common-corruption settings. Across a wide range of state-of-the-art adversarial training methods, we uncover a recurring failure mode: several approaches improve robust accuracy while degrading uncertainty ranking, leading to poorer selective behavior. To address this, we propose Evidential Adversarial Training (EV-AT), which models uncertainty through a Dirichlet distribution and combines (i) an evidence-based loss promoting clean accuracy and reliable uncertainty with (ii) a robust evidence-alignment loss matching clean and adversarial predictions in log Dirichlet-parameter space. Extensive experiments show that EV-AT shifts the Pareto frontier of robustness-uncertainty trade-offs beyond prior state-of-the-art adversarial training methods. Our source code is publicly available at https://github.com/NicolasSournac/Robustness_Meets_Uncertainty.EV-AT.

Explainability is central to building trustworthy AI, yet explanation interfaces can inadvertently provide adversaries with an expanded privacy-related attack surfaces. Recent studies show that advanced membership-inference attacks succeed by exploiting confidence-drop trajectories, induced through attribution-guided perturbations, as discriminative features, rather than directly using confidence scores or explanation vectors. Existing defenses against membership inference fail to directly mitigate such explanation-driven attacks. In this work, we investigate whether, during training, a model's own gradients can be leveraged as defense signals against such attacks, thereby aligning explanation profiles between members and non-members. To this end, we propose a Trajectory-Invariant Explanation Regularization (TIER) defense that penalizes erratic fluctuations in confidence drops simulated through gradient-guided perturbations and simultaneously minimizes the distributional shifts via KL-divergence. Unlike conventional adversarial training, which emphasizes label robustness, our approach targets explanation robustness by enforcing self-consistency through KL-divergence and reducing the variance of confidence drops between members and non-members. Extensive experiments confirm that our method effectively mitigates these attacks, delivering privacy protection while maintaining model utility and explanation fidelity.

We develop a framework for analyzing the learning dynamics of $\ell_2$-adversarial training of single-index models on Gaussian mixtures in the high-dimensional limit under streaming stochastic gradient descent (SGD). We derive deterministic equivalents for a broad class of statistics of the SGD iterates, including the adversarial risk and distance to adversarial optimality, in terms of the solution to a system of ODEs. We use them to study two idealized learning rate schedules: the Polyak stepsize and exact line search. In the case of $\ell_2$-adversarial least squares with a single class, we show that, unlike noiseless standard least squares, no constant learning rate guarantees monotone descent of SGD towards a minimizer of the adversarial risk. We identify anisotropic covariance and a mismatch in ridge parameters as the main sources of suboptimality of exact line search relative to the Polyak stepsize. We also introduce a stochastic differential equation (SDE), called adversarial homogenized SGD, that captures the evolution of statistics of the iterates of SGD. For $\ell_2$-adversarial least squares, using this SDE, we show the evolution of the risk is equivalent, up to dimension-free constants, to that of SGD on standard least squares with an adaptive learning rate and adaptive $\ell_2$-regularization. When the dynamics converge, the limiting adversarial risk and SGD iterate are determined by a fixed-point equation, with the limiting iterate being equivalent to the solution of a ridge regression problem whose regularization parameter is the limiting effective regularization of SGD.

Rapid advancements in generative speech technology have compromised the reliability of voice biometrics. While current spoofing detectors excel when assessed under in-domain conditions, generalisation to out-of-domain settings is often poor. We show that this can be due to linguistic bias. A reliance on linguistic cues observed in training data can then compromise robustness to cross-data. We propose a linguistic-invariant spoofing detection framework utilizing teacher-student adversarial learning. The linguistic-aware teacher model, pre-trained on linguistic content of an external dataset, guides the student detector via gradient reversal to minimize the linguistic information. To prevent the inadvertent removal of non-linguistic cues, we incorporate a Variational Information Bottleneck to enable suppression of principal cues. Across nine DF Arena datasets, our method achieves up to a 36.2% relative reduction in the EER compare to the baseline.

Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absence of reliance on the target model and its output information, transferable adversarial attacks exhibit a notably high stealthiness and detection difficulty, making them a significant focus of defense. In this work, we propose a deep learning defense known as multi-source adversarial perturbations elimination (MAPE) to counter diverse transferable attacks. MAPE comprises the single-source adversarial perturbation elimination (SAPE) mechanism and the pre-trained models probabilistic scheduling algorithm (PPSA). SAPE utilizes a thoughtfully designed channel-attention U-Net as the defense model and employs adversarial examples generated by a pre-trained model (e.g., ResNet) for its training, thereby enabling the elimination of known adversarial perturbations. PPSA introduces model difference quantification and negative momentum to strategically schedule multiple pre-trained models, thereby maximizing the differences among adversarial examples during the defense model's training and enhancing its robustness in eliminating adversarial perturbations. MAPE effectively eliminates adversarial perturbations in various adversarial examples, providing a robust defense against attacks from different substitute models. In a black-box attack scenario utilizing ResNet-34 as the target model, our approach achieves average defense rates of over 95.1% on CIFAR-10 and over 71.5% on Mini-ImageNet, demonstrating state-of-the-art performance.

Synthetic data mitigates the data scarcity problem in autonomous driving perception. However, the synthetic-to-real gap leads to performance degradation, hindering real-world model generalization. Although current methods leverage diffusion models for photorealistic style transfer to bridge this gap, they critically ignore a practical asymmetry: while synthetic data possesses perfect pixel-level annotations, real-world style reference images generally lack corresponding labels. Consequently, existing methods relying on symmetric semantic guidance suffer from either prohibitive annotation costs or severe semantic misalignment. To address this dilemma, we formally propose a novel task: Asymmetric Style Transfer for Autonomous Driving (ASTAD), which requires semantically consistent transfer using only labeled synthetic content and unlabeled real-world references. We further introduce the ASTModel, a training-free two-stage framework designed to bridge this domain gap under asymmetric constraints. ASTModel first extracts a coarse semantic prior from the unlabeled target, followed by dynamic prior refinement and class-consistent style injection during the denoising process. Extensive experiments demonstrate that ASTModel significantly outperforms existing methods in downstream perception utility and structural fidelity, while offering a 3.2$\times$ inference speedup. This work aligns synthetic-to-real adaptation with practical constraints, holding the potential to accelerate the scalable deployment of robust autonomous driving systems. Code: https://github.com/Dingyi-Yao/ASTAD.

The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks. While prior defenses reduce their impact via pruning, masking, or feature recalibration, we instead propose to jointly learn to amplify and attenuate these signals through a simple activation scaling mechanism. To this end, we introduce Activation Amplification and Attenuation (A3), a lightweight plug-in module that enhances adversarial robustness with minimal modifications of the activations. A3 dynamically rescales the activations using a learnable mask and a scaling factor derived from the original activation magnitudes. The influence of adversarial perturbations can be amplified or attenuated using the same learnable parameters by simply flipping the sign of the scaling operation. The amplified signals serve as negative references to construct novel contrastive and ranking loss functions. Experimental analysis shows that learning to degrade the predictions in amplification mode simultaneously improves adversarial robustness in attenuation mode. Moreover, A3 relies on only a small number of learnable parameters, with most of its behavior being determined by the scaling mechanism rather than additional network capacity. Extensive experiments demonstrate that integrating A3 into different backbones, datasets, and training methods consistently improves adversarial robustness while introducing negligible computational and memory overhead compared to existing plug-in modules. Code is available at: https://github.com/tgoncalv/A3.

Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust statistical methods. In this context, we propose a two-stage Adversarial Contamination-resistant Iterative Hard Thresholding (AC-IHT) algorithm for high-dimensional regression with contamination. Our nonconvex algorithm achieves minimax near-optimal (up to logarithmic terms) estimation by iteratively updating the coefficient vector and the contamination vector with different thresholding scales. We further demonstrate that our AC-IHT estimator is signal-adaptive: under proper signal conditions, it adaptively attains a sharper estimation rate and more accurate support recovery. Moreover, it enjoys the strong oracle property, laying a theoretical foundation for asymptotic inference. Numerical experiments confirm its superior finite-sample performance. Finally, we discuss theoretical extensions of the proposed procedure to generalized linear models and to heavy-tailed noise settings.

Deep neural networks (DNNs) have shown outstanding performance in visual recognition tasks within vision sensor networks; however, they are still vulnerable to adversarial manipulations and imperceptible perturbations that can lead to erroneous predictions. To address that, this paper presents AEGIS, a semantic aware and uncertainty guided adversarial detection framework designed for robust image classification in vision sensors pipelines. At its core, a SemantiGAN module functions as a multi class semantic discriminator, identifying and filtering visually inconsistent adversarial inputs before they propagate further in the pipeline. For inputs that pass this stage, a stochastic augmentation process generates test time variations, from which handcrafted instability metrics FlipScore, Prediction Inconsistency, Layerwise Cosine Similarity (early and mid layers), and Entropy are computed. These features are aggregated into a compact five dimensional vector and processed by an Evidential Deep Learning (EDL) classifier, which models output evidence using a Dirichlet distribution to yield both class predictions and calibrated uncertainty estimates. Evaluations on the Tiny ImageNet dataset across six categories clean, FGSM, PGD, patch based, functional, and geometric attacks demonstrate the effectiveness of AEGIS. The proposed framework achieves an AUROC of 92.1%, an AUPRC of 90.2%, and an accuracy of 90.7%, outperforming conventional softmax-based detectors in terms of detection performance, robustness, interpretability, and uncertainty calibration.

Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes, resulting in poor generalization on minority groups. Bias mitigation remains challenging due to two fundamental issues. First, when group labels are unavailable, existing group-unsupervised methods typically infer spurious attributes implicitly from model behavior, making it difficult to identify spurious factors that are semantically aligned with real-world biases. Second, even with pseudo spurious supervision, most existing debiasing methods follow a single-branch design that operates within a single shared feature space, where target and spurious attributes are intrinsically entangled. To address the first challenge, we introduce Confidence-guided Bias Concept Mining (CBCM), which leverages diffusion-disentangled, semantically grounded concept representations to identify reliable spurious attributes without attribute annotations. To address the second challenge, we propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches and explicitly removes spurious information through cross null-space projection while preserving target-relevant semantics. Extensive experiments on four benchmark datasets show that our method achieves state-of-the-art worst group accuracy among group-unsupervised approaches, while tuning at most 0.22% of the model parameters. The source code is available in the supplementary materials.

Reinforcement learning can train bimanual dexterous hands to play piano in physics simulation with high note accuracy, but for high-DoF dexterous hands, relying solely on task rewards or IK inversion often leads to unnatural postures and joint overextension. We propose \textit{Adversarial Posture Regularization (APR)}. It avoids expensive, song-aligned expert demonstration data and instead uses a small amount of casual human playing data. By matching the distribution of the posture of the policy with the human prior through an adversarial objective, APR encourages more human-like hand shapes. Meanwhile, we collect and release unstructured hand motion data of piano playing using a consumer-grade Meta Quest 3, and retarget the key motion information to the Shadow Hand. Finally, we achieve significantly better performance than prior methods on all three human-likeness metrics (cPSI, BSE, and FAC) as well as in visual quality. Project repository: https://github.com/APRProject/APRPianist.

Input Diversity (DI), a random resize and pad applied at each attack iteration, is a near-default ingredient of transfer-based attacks, widely assumed to improve transferability. We show this assumption is regime-dependent and, for adversarially trained surrogates, often reversed. Holding the attack fixed and varying only the surrogate, raising the DI probability improves transfer from standard surrogates but degrades it from robust ones: the two response curves separate like a pair of scissors, a pattern we call the Scissors Effect. On ImageNet, blind DI costs a robust source 10.3 percentage points of attack success across four architecturally diverse targets; the effect is several times smaller at 32x32. Direct measurement supports a bias-variance account: DI displaces the gradient by a comparable amount on both groups but reduces its variance only where the gradient is noisy, and robust surrogates have little noise left to average away. A gradient-consistency probe, frozen and hashed before the runs, predicts the sign of the effect on seven unseen surrogates, and we report where it fails alongside where it works. The practical consequence holds independently of the mechanism: leaving DI enabled by default understates the attack a robust surrogate can mount, and so overstates the robustness of the model being evaluated. Code: https://github.com/Avalon-S/ScissorsEffect.

Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupted inputs also destabilize online updates. We study robust test-time adaptation (RTTA) in the adversarial-stream setting, which remains comparatively underexplored relative to standard TTA, and propose SAFER (Stochastic Augmentation Framework for Enhanced Robustness), a training-free reliability-guided augmentation wrapper for RTTA. SAFER preserves the wrapped TTA objective while replacing brittle single-view predictions with a reliability-guided pooled predictor. For each test sample, SAFER generates stochastic augmentations and aggregates their predictions through correlation-weighted pooling with outlier detection. We further study an adaptive-mixing extension that improves clean-performance retention by adjusting original-versus-augmentation weighting using feature disagreement signals. We evaluate on PACS, VLCS, and OfficeHome under PGD attacks at various attack rates. Across benchmarks, SAFER improves resilience of TTA methods to adversarial attacks while maintaining competitive clean performance.

Multi-threat robustness remains a fundamental challenge in deep learning. Although joint adversarial training (JAT) is widely adopted, it suffers from negative transfer under heterogeneous threats, particularly between $\ell_p$-bounded and semantic attacks. Through first-order gradient analysis, we formalize this as gradient incompatibility and theoretically establish the necessity of decoupled optimization. We further reveal that these conflicting threats exhibit separable spectral characteristics in the frequency domain. Motivated by this observation, we propose Threat-aware Frequency Decoupling (TaFD), a two-stage defense framework that reformulates JAT as a frequency-domain divide-and-conquer paradigm. TaFD first discovers latent threat domains via unsupervised clustering of attack spectral prototypes and trains a lightweight classifier for inference-time threat domain identification. Conditioned on the prediction, TaFD employs a Frequency-Conditional Convolution that learns threat-domain-specific spectral masks and routes each sample to the corresponding expert, enforcing structural parameter separation and alleviating optimization conflicts. We validate TaFD on three representative image-classification benchmarks (CIFAR-10, CIFAR-100, and Tiny-ImageNet) and on two representative architectures (the convolutional ResNet and the hybrid-transformer MobileViT). Extensive results demonstrate that TaFD achieves more balanced robustness against heterogeneous attacks than existing JAT and frequency-domain baselines, improving average robust accuracy by approximately 11% over the strongest baseline while maintaining leading clean accuracy.

Time-series forecasting models remain vulnerable to gradient-based adversarial attacks while existing defense mechanisms typically incur a trade-off in robustness for bounded response and compute cost. The problem is pronounced in Moving Target Defense where maintaining multiple randomized model instances substantially exacerbates the training overhead. In this work, we introduce MorphStrata, a student generation strategy with selective, layer-specific stochastic noise injection that extends the traditional Morphence defense. MorphStrata uses a Transformer backbone as the teacher and perturbs randomly selected architectural blocks to create structured heterogeneity across student models in response to varied data distributions and threat models. We evaluate against vanilla Transformer and Morphence backbones on a suite of benchmarks including the Jena Climate, Electricity Load Diagrams, and Appliances Energy Prediction using FGSM, BIM and PGD attacks across multiple attack strengths. Across datasets and attack regimes, the proposed ensemble maintains comparable adversarial RMSE. Specifically, for high entropy, periodic datasets as in the case of the AEP data, MorphStrata achieves the lowest RMSE across all attacks and perturbation budgets, improving over the static baseline by up to 24.11% and 97.97% under FGSM and BIM respectively at an epsilon value of 0.5 over 30 randomized trials. Targeting the layers to generate MorphStrata students accounts for less than 1% increase in train-times over the Morphence MTD baseline for most of the experiments, while accounting for double digit gains in adversarial RMSE reduction. We also observe a positive correlation between higher pairwise L2 distance (among generated students) and overall defense effectiveness. In summary, MorphStrata maintains adversarial robustness as an MTD defense at marginal cost deltas when compared to existing baselines.

Automated transcription of parliamentary proceedings faces significant hurdles due to demographic bias, dialectal variation, and technical artifacts such as utterance truncation during segmentation. This paper introduces the ROManian PARliamentary Speech Corpus (ROMPAR) dataset, a 17.80-hour corpus of Romanian and Moldavian parliamentary speech, featuring double-annotated ground truth and explicit labels for reconstructed word fragments. To build a robust ASR system, we propose a multi-task adversarial training framework that enforces demographic invariance across age, gender, and dialect. We address the inherent instability of adversarial objectives in generative architectures by introducing an exponential decay mechanism for the adversarial coefficients. Furthermore, we implement an LLM-guided decoding strategy with position-dependent weighting to facilitate morphological completion of truncated terminal words. Our results demonstrate that the proposed framework significantly reduces WER and achieves an F1-score of 96.6% in morphological reconstruction.

Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage. We propose TriAdReview, a triangular adversarial review architecture that employs two independent reviewer models (engineering and boundary perspectives) and a triangular judging mechanism to iteratively improve a generator model's output. We evaluate TriAdReview across five benchmark tasks - architecture design, code generation, proposal review, security audit, and requirements analysis - using three configurations: single model (baseline), dual model (single review), and triple model (full system). Results across 75 experiments (n=5 per cell) show that the triple model configuration achieves a 10.1% overall improvement over the single model baseline (26.2 vs. 23.8 out of 50; p<0.05, paired t-test), with particularly strong gains on security audit (+27.6%), code generation (+20.8%), and architecture design (+15.6%). A second scorer (mimo-v2.5-pro) confirms the direction with a smaller effect (+2.7%), suggesting moderate inter-rater agreement. However, the system shows a -7.5% degradation on requirements analysis, revealing that adversarial review architectures have a structural bias toward simplification that is counterproductive for completeness-oriented tasks. We analyze this boundary condition through a task-type framework and demonstrate that reviewer prompt adaptation partially mitigates the issue. Our findings provide the first empirical characterization of when multi-model adversarial review helps versus harms, with implications for the design of collaborative AI systems.

Adversarial Training (AT) improves neural network robustness, but most methods train a fixed parameter space from the start. This paper asks whether the order in which parameters become optimizable can affect the final robust solution, even when the final architecture or computation budget is controlled. We propose GRAPE, Guided Parameter-Space Evolution, a training framework for compact adversarial robustness. GRAPE combines parameter-space stabilization with progressive hidden expansion: it stabilizes robust optimization in the currently exposed space, gradually releases new optimizable dimensions, and uses an adversarial spectral utilization score to guide newly released capacity toward high-pressure modules. In contrast to fixed-structure AT, GRAPE treats robust model learning as a process of progressive parameter-space exposure and evolution. Under the standard $\ell_\infty$ threat model on CIFAR-10, with fixed-structure ResNet-18 AT as a controlled reference, GRAPE improves PGD-20 robust accuracy from 51.70% to 56.94% at a nearly matched computation budget with a FLOPs ratio of 1.009x, while reducing parameter count by about 21.4%. A sequential grow variant with the same final ResNet-18 architecture reaches 56.52% PGD-20 robust accuracy, indicating that the gain is not only due to final architecture differences but also to the parameter-space exposure path. These results suggest that guided parameter-space evolution can yield compact and robust parameter configurations under matched computation.

Closed-loop adversarial training improves autonomous driving safety by exposing policies to rare safety-critical scenarios. Standard pipelines first generate adversarial scenarios and then sample them for policy optimization. However, most existing frameworks remain attack-oriented: collision-driven generators often synthesize unsolvable extreme situations, which can degrade learning, while heuristic samplers ignore the evolving capability of the driving policy, causing sample inefficiency and delayed convergence. We propose AlignADV, a learnability-guided closed-loop adversarial training framework that converts adversarial scenarios into resolvable and capability-aligned curricula. First, we reformulate adversarial scenario generation as a preference alignment problem and employ direct preference optimization to guide the generator toward critical yet resolvable scenarios. Second, we introduce behavioral fingerprints to capture the intrinsic characteristics of the evolving policy and construct a multi-modal capability prediction model that estimates policy performance without expensive closed-loop simulations. By combining resolvability-aligned scenarios with capability predictions, AlignADV develops a dynamic curriculum sampling mechanism that prioritizes scenarios targeting the current policy's vulnerabilities. Experiments on the Waymo Open Motion Dataset demonstrate that AlignADV improves convergence efficiency and final performance, reducing training steps by up to 40.6 percent compared with baseline methods while lowering collision rate and improving route completion under both normal and adversarial traffic conditions. These results highlight a shift from attack-oriented scenario generation to learnability-guided policy improvement, offering a principled direction for safer and more efficient autonomous driving training. Project page: https://meiyuewen.github.io/AlignADV/.

Purpose: To investigate whether contrast-informed data augmentation and domain-adversarial training improve the adult-to-neonatal generalization of the E2E-VarNet. Methods: Three training regimes were investigated: (1) adult-only training with unaugmented adult data, (2) mixed training with paired unaugmented and neonatal-informed augmented adult data, and (3) mixed training with a domain-adversarial objective. Models were trained on retrospectively undersampled multi-coil adult T2-weighted brain MR data and evaluated on neonatal and adult test data at acceleration factors $R=4$ and $R=8$ using quantitative metrics and qualitative evaluation. Feature analyses assessed whether domain-adversarial training altered the latent representations of unaugmented adult, augmented adult, and neonatal test samples. Results: Mixed training (Mixed) and mixed domain-adversarial training (Mixed-DAT) outperformed unaugmented adult-only training (Unaug-Only) when evaluated on neonatal data. At R=4, Mixed-DAT achieved the best performance (SSIM = 0.924 +/- 0.027, PSNR = 33.98 +/- 1.15 dB). At R=8, Mixed-DAT performed best when measured using SSIM (0.848 +/- 0.031 vs. 0.766 +/- 0.037 for Unaug-Only and 0.814 +/- 0.035 for Mixed) and Mixed performed best when measured using PSNR (29.56 +/- 0.83 dB vs. 26.26 +/- 0.78 dB for Unaug-Only and 29.43 +/- 0.83 dB for Mixed-DAT). Qualitative assessment of t-SNE plots suggested that Mixed-DAT increased the overlap among the latent representations of the unaugmented adult, augmented adult, and neonatal test data. Conclusion: Contrast-informed augmentation and domain-adversarial training improved adult-to-neonatal generalization of deep learning-based MR reconstruction. These findings suggest that contrast-informed data augmentation combined with adversarial training may improve robustness to domain shift in undersampled neonatal MR reconstruction.

We study six production image-to-image AI systems (gpt-image-1, Gemini 2.5 Flash Image, Flux Kontext, SDXL img2img, SD3 img2img, and Qwen Image Edit) under a content-adaptive sub-JND adversarial perturbation pipeline, scoring all outputs by frozen DINOv2 ViT-B/14 token distances against clean references. Across a 3,588-call corpus spanning COCO photographs, CelebA-HQ portraits, and AI-generated inputs, the six systems partition into two image-invariant behavioral bands on a 2D (patch_mean, ssim_clean) plane: edit-trained models (Flux Kontext, Qwen Edit, Gemini) cluster in a tight band, while T2I-base models adapted at sampling time (SDXL, SD3, gpt-image-1) cluster in a drift band.

Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations. To address this, we investigate whether reinforcement learning (RL) training can disrupt the gradient structure used by attackers by training image classifiers with policy-gradient objectives and epsilon-greedy exploration. Through systematic experiments across CIFAR-10, CIFAR-100, and ImageNet-100 with multiple architectures, we find that RL-trained classifiers significantly disrupt gradient-based adversarial optimization. To explain this, we conduct a comprehensive mechanism analysis using loss landscape visualization, static and dynamic gradient indicators, and predictive entropy. Our analysis reveals that RL acts as an implicit regularizer, producing models with highly unstable gradient directions and smaller gradient magnitudes. This combination makes each PGD step both unreliable in direction and limited in magnitude, causing gradient-based attacks to fail within practical iteration budgets. We further show that combining RL with adversarial training (RL-adv) provides a dual-layer defense operating at two complementary levels: RL degrades gradient information available to attackers (gradient-level defense), while adversarial training strengthens decision boundaries (boundary-level defense). RL-adv achieves the highest robustness across all major attack types evaluated, including gradient-based (PGD, AutoAttack), transfer-based, and query-based attacks, outperforming SL-adv by a significant margin. These findings identify RL-induced gradient disruption as a complementary robustness mechanism and motivate future research on hybrid SL-RL training schedules that combine SL's efficiency with RL's gradient-regularization properties.

Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness. A key property is cross-model transferability, which enables transfer-based black-box attacks. However, existing attacks often rely heavily on the surrogate model, causing cross-model performance drops. One reason is that adversarial optimization may follow surrogate model responses more than input semantics, making the update direction effective on the surrogate but less transferable to unseen targets. We refer to this dependency as surrogate-specific bias. Motivated by this observation, DeBias-Attack improves transferability by correcting surrogate-specific bias in adversarial optimization directions. It maintains two perturbation branches. The main branch optimizes a perturbation on the original image and obtains the adversarial gradient used to disrupt image-text alignment. The reference branch optimizes a perturbation on a weak-semantic image constructed from the dataset mean image with small Gaussian noise resampled at each iteration. Since this weak-semantic image contains little clear visual content, its optimization reflects surrogate responses more than image semantics, and its reference gradient estimates surrogate-specific bias. DeBias-Attack removes the aligned projection of the main gradient on the reference gradient before updating the adversarial image, then performs context-aware text substitution using the updated adversarial image. DeBias-Attack is the first transfer-based VLP attack that corrects surrogate-specific bias through gradient correction. Experiments show strong performance across VLP models, downstream tasks, and open-source and closed-source multimodal large language models.

With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing verification methods either rely on overly conservative approximations or incur prohibitive computational costs. For example, the use of lp-norm perturbations in video settings encodes the belief that the adversary can inject noise in every video frame. In practice, adversarial perturbations exhibit structured spatial and temporal correlations, constrained to lower-dimensional, semantically meaningful subspaces. In this work, we study robustness verification of 3D CNNs processing video and volumetric inputs, targeting applications in action recognition (UCF-101), autonomous driving (Udacity), and medical imaging (MedMNIST) exploiting realistic assumptions on adversarial strength by modelling them as spatio-temporal constraints - where the attacker can modify either a subset of frames or patches within a set of consecutive frames. We demonstrate that modelling realistic constraints enables tighter approximations. We introduce Spatio-Temporal Bound Propagation (STBP), a verification framework that computes an exact closed-form characterization of the first convolutional layer and propagates certified bounds through subsequent layers using scalable approximations. Computing the exact closed form provides the tightest bounds for the first convolutional layer. Thus, we utilise approximation methods in the remainder of the network. To spur further progress in this field, we propose ST-Bench, a verification benchmark for autonomous driving and activity recognition, to systematically evaluate verifiable robustness. Compared to existing verification-based approaches, STBP provides stronger robustness guarantees with significantly improved scalability, achieving 1.7x higher certified robust accuracy under identical perturbation budgets.

While confidence calibration is essential for trustworthy decision-making in safety-critical applications, the robustness of calibrated GNNs to adversarial structural perturbations remains largely unexplored. However, studying calibration attacks on graphs presents unique technical challenges: (1) the discrete nature of graph structures complicates gradient-based optimization, (2) existing underconfidence objectives fail to drive predictions toward uniform distributions, and (3) GNNs are highly sensitive to edge perturbations, often causing unintended label changes that violate attack constraints. To address these challenges, we propose a \textbf{Unified Graph Calibration Attack (UGCA)} framework designed for \textbf{worst-case (white-box) analysis} of GNN calibration robustness. UGCA introduces a KL-divergence loss to encourage uniform predictive distributions, a reranking mechanism to reduce label flipping, a hybrid loss to recover labels when violations occur, and beam search to explore a broader adversarial search space. We further provide theoretical insights linking model generalization, dataset complexity, and calibration vulnerability, showing that models with higher accuracy or trained on datasets with more classes are more susceptible under this threat model. Extensive experiments demonstrate that UGCA substantially increases Expected Calibration Error while preserving classification accuracy. Our code is publicly available at https://github.com/CaptainCuong/Graph-Calibration-Attack.git.

Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations. Recent test-time adaptation defenses improve robustness by leveraging many augmented views, but this leads to impractical slowdown and a clear robustness-throughput trade-off. To address this challenge, we present Stability and Suitability-guided Test-time Prompt Tuning (SS-TPT), evaluating the quality of each augmented view via two complementary scores: (1) stability, measuring prediction invariance to weak augmentations, and (2) suitability, measuring feature-space density among views. These stability and suitability (SS) scores guide both adaptation and inference through an SS-guided consistency loss and an SS-weighted prediction, amplifying trustworthy views while suppressing corrupted ones. Extensive experiments demonstrate that SS-TPT significantly outperforms prior state-of-the-art methods, achieving superior robustness-throughput trade-offs across diverse datasets and varying numbers of views, thereby demonstrating both strong practicality and generality. Our code is available at https://github.com/sunoh-kim/SS-TPT.

LLM-driven automated penetration testing agents are typically evaluated against static targets that neither detect nor respond to attacks, so their behavior under intelligent defense remains untested. The causal consistency of multi-step attack chains likewise hinges on unstable LLM reasoning, and agent decisions remain opaque to human analysts. These three shortcomings, in realism, consistency, and auditability, are usually patched in isolation. We present ZERO-APT, a turn-based attacker-defender-judge framework that addresses them within a single architecture. For realism, ZERO-APT embeds a configurable LLM Defender that consumes Sysmon telemetry and detects attacks in real time, exposing the attacker to a live opponent rather than a passive target. For consistency, three architectural mechanisms move causal consistency from unstable LLM reasoning into enforced system architecture: separation of planning from execution, multi-dimensional ReAct feedback, and a hard-constraint-filtered action library. For auditability, a dedicated Judge agent adjudicates each round, maintains global state, and emits structured post-hoc CTI reports that make every decision traceable. We evaluate a Windows Server 2022 post-exploitation prototype across five scenarios with three Defender configurations. ZERO-APT reaches 79% attack success rate (Aurora 22%, PentestGPT 39%), a Causal Consistency Score of 0.860 (Aurora 0.930, Claude Code 0.520), and end-to-end decision auditability through structured CTI reports. We release the benchmark to support evaluation of penetration agents under intelligent defense.

Inverse adversarial training leverages high-confidence predictions to stabilize robust learning, yet we uncover a critical paradox: high confidence often stems from overfitting to non-causal background correlations rather than intrinsic object semantics. Our investigation reveals that visual context functions as a dual-natured signal, serving as either a necessary supportive prior or a spurious confounder. This insight renders existing blind suppression strategies flawed, as they inevitably lead to severe Feature Loss. To resolve this, we propose High-Confidence Causally Aligned Training (HICAT), a unified framework that establishes a Semantic Equilibrium. Operating on a ``Measure-Debias-Align'' pipeline, HICAT integrates a Learnable Background-Bias Estimator (LBBE) to adaptively diagnose context utility. Guided by this diagnosis, an Adaptive Debiasing mechanism performs surgical logit rectification, complemented by a geometrically grounded Foreground Logit Orthogonal Enhancement (FLOE) loss to enforce rigorous feature disentanglement. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that HICAT consistently improves over matched baselines across diverse architectures (CNNs and ViTs) while significantly reducing the robust generalization gap.

In dynamic environments, large language models need to keep adapting to new tasks, but continual learning often suffers from forgetting, limited transfer, and vulnerability to adversarial perturbations. To address this, we present AdvCL, which repurposes adversarial perturbations as a geometric control signal for stable continual adaptation. AdvCL combines three plug-in modules: Intra-Smooth promotes local smoothness via small adversarial perturbations; Proto-Clip uses similarity clipping to prevent excessive alignment to current task prototype; and Inter-Align applies directional alignment toward previous task prototype to reduce representational gaps. Experiments show consistent gains in both standard performance and robustness, with lower forgetting and stronger transfer. We further analyze key mechanisms by quantifying the sensitivity of Intra-Smooth to perturbation settings and the effect of Inter-Align on task similarity and geometric distance. In summary, the modules provide complementary gains when combined, and each can also be integrated individually into diverse CL paradigms, including replay, regularization, and dynamic architectures, thereby offering a geometric control mechanism for continual learning.

The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment. Existing techniques to enhance deep network robustness rely on adversarial training, an approach that is powerful but computationally intensive and typically tailored to specific attack types. To address these limitations, existing works have explored techniques such as adding gaussian noise or filtering images, both of which can boost the network robustness to various adversarial attacks, albeit modestly. Here, we theoretically demonstrate that these two approaches enhance robustness against adversarial attacks through complementary mechanisms, resulting in supralinear robustness when combined. Building on this insight, we experimentally show that a simple preprocessor combining Gaussian noise and bilateral filtering yields supralinear improvements in adversarial robustness with minimal computational cost. Next, we combine our preprocessor with adversarial training and test on RobustBench to assess its supralinear improvement over state-of-the-art defenses. First, this combination ranks second on AutoAttack and third overall, while using only $\sim$35% of the training FLOPs, using a model with $\sim$50% less parametets, trained with $\sim$33% of the epochs and $\sim$15% the data compared to state-of-the-art defenses. Second, our method scales efficiently, matching the accuracy of competing models with roughly 2-8x less total compute across 3 orders of magnitude. Overall, our approach provides a principled and easily integrable framework for enhancing adversarial robustness, offering negligible computational overhead and a simple yet theoretically grounded design.

Modern neural networks are highly susceptible to adversarial perturbations. In this work, we identify that part of this vulnerability stems from the sensitivity of the widely used fully connected (FC) classifiers to such perturbations. In contrast, simple $\ell_2$ distance-based classifiers exhibit significantly greater robustness. We provide thorough theoretical and empirical analysis showing that while FC classifiers' high sensitivity makes them discriminative, it also makes them vulnerable. Conversely, $\ell_2$-classifiers' insensitivity grants robustness but limits performance. Motivated by this trade-off, we propose a novel $\ell_2$-reclassifier based on a Hybrid Prototype Mixing (HPM) framework. This method retains the discriminative power of FC classifiers while leveraging the robustness of $\ell_2$ distance. It yields $\ell_2$-distance-based predictions by fusing two prototype types: (1) stable, dataset-level prototypes updated via EMA, and (2) dynamic, batch-level prototypes generated from the FC classifier's predictions using a Straight-Through Estimator (STE). However, this dynamic, STE-based architecture introduces significant challenges for evaluation, such as gradient obfuscation and forward discontinuity. To address this, we propose a new, rigorous evaluation protocol, the Mixed Surrogate Attack (MSA), which uses multiple surrogates along with powerful AutoAttack to ensure a fair and robust assessment. Extensive experiments demonstrate that our lightweight, plug-and-play module, with minimal fine-tuning, effectively enhances the adversarial robustness of various existing SOTA adversarially trained models.

Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-step variants, where robustness to multi-step attacks collapses despite high single-step performance. We address this failure mode with two contributions. First, we formalize Epsilon Overfitting (EO), a perspective in which fixed perturbation magnitudes and directions exacerbate CO, and show that introducing perturbation variability significantly improves robust generalization across different architectures and datasets. Second, we propose PertAlign (Perturbation Alignment), a theoretically grounded, computationally negligible metric that predicts CO onset by measuring gradient alignment across attack stages. Leveraging these insights, we introduce SORA, an adaptive step-size AT method that dynamically adjusts perturbations based on loss surface geometry. SORA consistently prevents CO, achieves state-of-the-art robustness and clean accuracy, and generalizes across datasets and architectures using a single fixed set of hyperparameters, which is essential for applicability in fast AT. Extensive experiments on diverse datasets and architectures show that SORA matches or surpasses the robustness of prior methods while delivering higher clean accuracy and superior efficiency. Code is available at https://github.com/SecondOrderAT/SORA.