Adversarial Training

Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowledge discovery. Prior work on automated publication type and study design indexing has primarily focused on expanding label coverage, enriching feature representations, and improving in-domain accuracy, with evaluation typically conducted on data drawn from the same distribution as training. Although pretrained biomedical language models achieve strong performance under these settings, models optimized for in-domain accuracy may rely on superficial lexical or dataset-specific cues, resulting in reduced robustness under distributional shift. In this study, we introduce an evaluation framework based on controlled semantic perturbations to assess the robustness of a publication type classifier and investigate robustness-oriented training strategies that combine entity masking and domain-adversarial training to mitigate reliance on spurious topical correlations. Our results show that the commonly observed trade-off between robustness and in-domain accuracy can be mitigated when robustness objectives are designed to selectively suppress non-task-defining features while preserving salient methodological signals. We find that these improvements arise from two complementary mechanisms: (1) increased reliance on explicit methodological cues when such cues are present in the input, and (2) reduced reliance on spurious domain-specific topical features. These findings highlight the importance of feature-level robustness analysis for publication type and study design classification and suggest that refining masking and adversarial objectives to more selectively suppress topical information may further improve robustness. Data, code, and models are available at: https://github.com/ScienceNLP-Lab/MultiTagger-v2/tree/main/ICHI

Decentralized multi-agent path finding (MAPF) routes a team of agents on a shared grid, each acting from its own local view. The standard solution trains one shared neural policy with Proximal Policy Optimization (PPO), a popular on-policy reinforcement learning algorithm. Such a policy works well on clean observations, but a small input perturbation on one agent often changes its action, which then blocks a neighbour, and the team jams. In this paper we present two training recipes that keep the same network and the same deployment loop, yet make the policy hold up under perturbed observations. The first recipe, Adv-PPO, trains the shared policy against worst-case perturbations of its own input and selects the checkpoint by performance under adversarial perturbation. The second recipe, Adv-PPO+MACER, fine-tunes that checkpoint with a small on-policy smoothness term whose gradient follows the certified radius of randomized smoothing. On POGEMA with 8x8 maps and four agents, the unprotected PPO policy reaches 95.8% clean success but only 2.5% under the strongest attack. Adv-PPO recovers worst-case success to 59.2% at one percentage point of clean cost. Adv-PPO+MACER recovers it to 77.5% +/- 6.0% across three independent seeds at less than one percentage point of clean cost. We support these numbers with per-attack curves, a certified action-stability sanity check (which measures the smoothed-policy wrapper, not the deployed argmax policy), and side-by-side rollout storyboards that show the failure mode and the fix inside one environment instance.

Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transitions that dominate downstream planning and policy performance. Because passive demonstration data systematically under-samples these high-impact regimes, improving robustness requires actively eliciting model failures rather than relying on their natural occurrence. We introduce a KL-constrained adversarial curriculum in which a policy is trained to expose high-error trajectories of a diffusion-based world model while remaining close to the behavior distribution. The world model is continuously fine-tuned on these adversarially discovered trajectories, yielding an adversarial training loop that converts rare failures into a stable, near-distribution training signal without drifting into out-of-distribution exploitation. To maintain pressure on unresolved weaknesses as the model improves, we propose a Prioritized Adversarial Trajectory (PAT) buffer that re-ranks trajectories based on prediction error, action fidelity, and learning progress, focusing training on unresolved failure modes rather than repeatedly revisiting solved cases. We implement our approach in the MineRL framework and evaluate it on held-out out-of-distribution trajectories; PROWL improves robustness over models trained on passive data alone, reveals reward-hacking behaviors under weak behavioral constraints, and demonstrates that effective adversarial world-model training critically depends on balancing exploratory failure discovery with explicit behavioral regularization. Our results suggest that scalable world models benefit not only from larger datasets, but also from selectively generating informative training data.

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversarial training methods have shown promising results in producing more robust classifiers, their interpretability and defense ability are limited due to their lack of understanding of how adversarial attacks propagate in different layers of network classifiers. In this paper, we present an insightful approach, called LARAR (Layer-wise Adversarial Robustness using Adaptive Regularization), that incorporates additional layer-wise vulnerability analysis and adaptive weighting in conventional adversarial training methods. Additionally, we utilize 'Auxiliary Classifiers' in our approach. LARAR provides interpretable layer-wise vulnerability scores, achieves a clean accuracy of 95.01%, and provides better robustness against adversarial attacks (FGSM, PGD, and transfer attacks) on the UNSW-NB15 dataset. Through the identification of vulnerable layers, the proposed framework reduces computational complexity and enables the early detection of adversarial samples, thus enhancing the effectiveness and interpretability of adversarial defense mechanisms in NIDS.

Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerable to novel attack vectors and distributional shifts. We propose Latent Personality Alignment (LPA), a sample-efficient defense that achieves robustness by training models on abstract personality traits rather than specific harmful behaviors. Using fewer than 100 trait statements and latent adversarial training, LPA achieves comparable attack success rates to methods trained on 150k+ examples, while maintaining superior utility. Critically, LPA generalizes better to unseen attack distributions, reducing misclassification rates by 2.6x compared to baseline across six harm benchmarks -- without ever seeing harmful examples during training. Our results demonstrate that personality-based alignment offers a principled approach to building robust defenses with minimal cost.

While spatiotemporal deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks. These models tend to overfit on fragile temporal spectrum cues, rather than learning robust semantic causality. To mitigate this vulnerability, we propose SpInShield, a temporal spectral-invariant defense framework explicitly designed to decouple semantic motion from manipulatable spectral artifacts. We propose a learnable spectral adversary that dynamically synthesizes severe spectral deformations, simulating extreme attack scenarios. By employing a shortcut suppression optimization strategy, SpInShield compels the encoder to extract reliable forensic cues while purging unstable spectral statistics from the latent space. Experiments show that SpInShield obtains competitive performance on widely used datasets and outperforms the strongest baseline by 21.30 percentage points in AUC under simulated amplitude spectral attacks.

Motivational-interviewing-based health coaching is an effective approach for improving mental health and promoting healthy behavior change. However, the scarcity of trained human coaches and the high cost of coaching services make such support inaccessible to many people who could benefit from it. This motivates the development of AI health coaches that can provide scalable and affordable support. Existing methods typically optimize only one side of the interaction: they either train a dialogue agent against a fixed client environment or train a client simulator against a fixed assistant. This one-sided setup can limit exploration of the interaction space and may be inefficient at developing the capabilities required by the target agent and pushing its performance boundaries. In this paper, we propose a dual-agent framework that interactively co-trains both the health coach agent and the client simulator. The coach is optimized with DPO using Pareto-dominant response pairs identified by a multi-dimensional LLM judge. In turn, the client is trained adversarially by reversing these preferences, inducing an implicit adversarial training dynamic. We further show that this co-training process admits a natural stochastic-game interpretation. Extensive experiments demonstrate that our method effectively improves coaching quality across several important dimensions.

Adversarial robustness has been studied extensively for offline deep networks, but less is known about strict single-pass streaming neural learners. This paper studies adversarial robustness in Fuzzy ARTMAP, an Adaptive Resonance Theory architecture based on category competition, complement coding, match tracking, and replay-free prototype updates. We introduce WB-Softmax, a differentiable white-box attack surrogate aligned with ARTMAP's category-competition and map-field prediction mechanism, and formalize a streaming evaluation principle requiring robustness to be assessed on the final deployed model. Across four image benchmarks, WB-Softmax achieves 89-100% attack success on vanilla Fuzzy ARTMAP models. We show that defense rankings can reverse across protocols: offline adversarial training may appear strong under transfer attacks yet collapse under adaptive white-box evaluation, whereas progressive two-stage selective training provides the strongest overall replay-free robustness. We further show that ART's explicit category geometry enables interpretable diagnosis of separation collapse and match-score inversion. These results provide a mechanism-aligned, protocol-aware framework for adversarial robustness in streaming prototype-based learners.

Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing defenses are largely limited to single-modal settings and mainly focus on poisoning-based threats, leaving evasion-based threats underexplored. In this work, we first identify a cross-modal gradient mismatch under the multi-user promotion setting, where visual and textual perturbations are optimized in inconsistent directions due to the dominance of distinct user groups. This phenomenon dilutes the attack effectiveness and leads robust training to underestimate worst-case risks. To address this issue, we propose Untargeted Adversarial Training with Multimodal Coordination (UAT-MC). UAT-MC tackles the challenge of unknown targeted items in evasion-based attacks (as opposed to poisoning-based attacks) by treating all items as potential targets, and introduces a gradient alignment mechanism to explicitly correct this mismatch. This design ensures synchronized perturbations across modalities, thereby maximizing adversarial strength for robust training. Extensive experiments demonstrate that UAT-MC significantly improves robustness against promotion attacks while maintaining acceptable recommendation performance under the defense-accuracy trade-off. Code is available at https://github.com/gmXian/UAT-MC.

Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to scale. Recent continuous adversarial training methods, such as Continuous adversarial training (CAT) and Continuous Adversarial Preference Optimization (CAPO), address this challenge by leveraging gradient-based perturbations in the embedding space, enabling more efficient and expressive attacks. Building on this paradigm, we propose WARDEN, a distributionally robust adversarial training framework for LLMs that dynamically reweights adversarial examples through an f -divergence ambiguity set around the empirical training distribution. Our method optimizes the worst-case adversarial loss within a divergence ball around the empirical data distribution, automatically emphasizing harder adversarial examples. Using the convex dual formulation, the objective reduces to a log-sum-exp form under the KL divergence, with a dynamical parameter controlling the strength of reweighting. This study leads to a new class of information-theoretic objectives that significantly reduce attack success rates while maintaining model utility. Across multiple LLMs and attack settings, WARDEN substantially reduces attack success rates with computational and utility costs comparable to CAT-, CAPO-, and MixAT-based baselines, making it a practical approach for scalable robust alignment.

Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often underperform in few-shot settings and remain vulnerable to adversarial, humanizing attacks. To build accurate and robust detectors under limited supervision, we adopt a threat-modeling perspective and study detector vulnerabilities from an attacker's viewpoint under an output-only black-box setting. Motivated by this perspective, we propose RAG-GuidEd Attacker Strengthens ConTrastive Few-shot Detector (REACT), an adversarial training framework that improves both few-shot detection performance and robustness against attacks. REACT couples a humanization-oriented attacker with a target detector: the attacker leverages retrieval-augmented generation (RAG) to craft highly human-like adversarial examples to evade detection, while the detector learns from these adversaries with a contrastive objective to stabilize few-shot representation learning and enhance robustness. We alternately update the attacker and the detector to enable their co-evolution. Experiments on 4 datasets with 4 shot sizes and 3 random seeds show that REACT improves average detection F1 by 4.95 points over 8 state-of-the-art (SOTA) detectors and reduces the average attack success rate (ASR) under 4 strong attacks by 3.66 percentage points.

Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose Manifold-Constrained Adversarial Training (MCAT), a unified framework that enforces the semantic validity of adversarial examples by penalizing deviations from class-conditional manifolds in feature space, while promoting balanced geometric separation across classes via an ETF-inspired regularization. We provide theoretical results that link geometric separation to lower bounds on adversarially robust margins, and show that manifold-constrained adversarial risk upperbounds robust risk on high-density semantic regions. Extensive experiments on standard longtailed benchmarks demonstrate consistent improvements in overall, balanced, and tail-class adversarial robustness.

Face Recognition systems are widely deployed in real-world applications, but they also raise privacy concerns due to unauthorized collection and misuse of facial data. Existing adversarial privacy protection methods rely on input-space perturbations to obfuscate identity information, yet their protection can degrade when adversaries learn restoration or purification mappings that partially invert the transformation. We study this setting as an asymmetric adversarial attack, in which reverse manipulation becomes feasible because existing defense paradigms do not control reversibility. To address this problem, we propose Asymmetric Reversible Face Protection (ARFP), a restoration-aware extension of personalized face cloaking that integrates privacy protection, keyed recovery, and tamper indication in a single framework. ARFP consists of three components: Key-Conditioned Manifold Binding, which ties the protection transformation to a user-provided key; Adversarial Restoration-Aware Training, which introduces a surrogate restoration adversary during training to improve robustness against evaluated inverse purification attacks; and Authorized Reversible Restoration, which supports recovery with the correct key while providing nonce-based tamper indication. Extensive experiments under the threat models considered in this work show that ARFP improves resistance to the evaluated restoration attacks while preserving authorized recovery utility. These results provide empirical evidence of key-sensitive recovery behavior and tamper awareness in the tested settings.

A speaker encoder used in multilingual voice cloning should treat the same speaker identically regardless of which script the audio was uttered in. Off-the-shelf encoders do not, and the failure is accent-conditional. On a 1043-pair Western-accented voice corpus across English, Hindi, Telugu, and Tamil, WavLM-base-plus-sv loses 0.082 absolute cosine similarity when the same voice changes script and ECAPA-TDNN loses 0.105. On a 1369-pair Indian-accented voice corpus, the gap shrinks to 0.006 (WavLM-SV) and 0.044 (ECAPA-TDNN). The leak is largest where it matters most for cross-script TTS: when a system projects a non-Indic-trained voice into Indic scripts. We present LASE (Language-Adversarial Speaker Encoder), a small projection head over frozen WavLM-base-plus trained with two losses: a supervised contrastive loss over voice identity, and a gradient-reversal cross-entropy against a 4-language classifier that pushes the embedding to be language-uninformative while remaining speaker-informative. Trained on 1118 quality-gated cross-script pairs synthesised from 8 commercial multilingual voices, LASE's residual gap is consistent with zero on both corpora (Delta = 0.013 Western, Delta = 0.026 Indian; both bootstrap 95% CIs include zero) and amplifies the cross-script-vs-floor margin 2.4-2.7x over both baselines. An ECAPA+GRL ablation shows the GRL objective improves either backbone but the WavLM choice contributes too. In synthetic multi-speaker diarisation, LASE matches ECAPA-TDNN on cross-script speaker recall (0.788 vs 0.789) with ~100x less training data. We release the r1 checkpoint, both corpora, and the bootstrap recipe.

Quantum machine learning is a promising field for efficiently learning features of a dataset to perform a specified task, such as classification. Interval bound propagation (IBP) is a popular certified training method in classical machine learning, where the lower and upper bounds are tracked throughout the model. These bounds are used during training to ensure that the model is certified to predict the correct label even under adversarial perturbations. While IBP is successful in classical domain, there are limited certified training efforts in quantum domain. In this paper, we present quantum interval bound propagation (QIBP) to establish a certified training routine for quantum machine learning, certifying the accuracy of models under adversarial perturbations. We implement QIBP using both interval and affine arithmetic to explore the tradeoffs between the two implementations in terms of accuracy and other design considerations. Extensive evaluation demonstrates that the resulting certified trained models have robust decision boundaries, guaranteed to predict the correct class for the samples within the trained adversarial robustness bounds.

Safety-aligned language models must refuse harmful requests without broad over-refusal, but it remains unclear how dynamic adversarial fine-tuning changes refusal-control carriers: Kullback--Leibler (KL)-constrained directions or small subspaces that causally modulate refusal without large safe-prompt distribution shifts. We study a 7B backbone under supervised fine-tuning (SFT) and Robust Refusal Dynamic Defense (R2D2), aligning HarmBench, StrongREJECT, and XSTest evaluations with five-anchor geometry measurements, causal interventions, and sparse adaptive stress tests. R2D2 drives fixed-source HarmBench attack success to zero at early checkpoints; however, these checkpoints also exhibit maximal XSTest refusal and fail a benign-utility audit. Later checkpoints partially recover utility-facing behavior while reopening attack success, with adaptive GCG attack success rate rising to 0.415 at step 250 and 0.613 at step 500. Internally, R2D2 preserves a late-layer admissible refusal-control carrier through step 100 and then relocates the best admissible carrier to an early layer; SFT relocates earlier yet remains less robust. Effective rank stays near 1.24, and SFT shows larger principal-angle drift, arguing against both dimensional expansion and drift magnitude as sufficient explanations. Causal interventions support a low-dimensional but utility-coupled carrier. These results support a geometry-reorganization account of R2D2 along a robustness--utility frontier, without establishing adaptive robustness.

As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat to scholarly integrity. We propose SafeReview, a co-evolutionary adversarial training framework for defending LLM-based peer review systems against such attacks. SafeReview jointly trains a Generator model to create sophisticated attack prompts and a Defender model to preserve review integrity under adversarial manipulation. The Generator is optimized to produce increasingly effective prompt injections, while the Defender is strengthened through preference-based training to maintain consistent reviews between clean and attacked submissions. Experimental results show that SafeReview improves robustness against adaptive prompt injection attacks, better preserves paper ranking under attack, and generalizes across attacker architectures compared with static defenses. These results demonstrate the potential of co-evolutionary training as a foundation for securing LLM-assisted peer review.

Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising phenomenon for the first time: Varying input perturbation intensities for training samples near decision boundaries in AT have minimal impact on model robustness. This finding directly exposes the inconsistency between accuracy and robustness score fluctuations, leading us to identify the misalignment between input and latent spaces as a critical driver of the robustness-accuracy trade-off. To mitigate this misalignment for harmonizing accuracy and robustness, we define Robust Alignment as a new AT target, encouraging the model perception to change with input perturbations provided the final label prediction remains unchanged, which can be achieved via two novel ideas. First, we suggest a reduced and fixed perturbation intensity for those boundary samples, which facilitates the model to utilize the perturbations as learnable patterns, instead of noises that complicate decision boundaries meaninglessly. Second, we propose a Domain Interpolation Consistency Adversarial Regularization (DICAR), based on rigorous theoretical derivations, which explicitly introduces semantic alignment between input and latent spaces into AT. Based on these two ideas, we end up with a new Robust Alignment Adversarial Training (RAAT) method, effectively harmonizing accuracy and robustness. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet with ResNet-18, PreActResNet-18, and WideResNet-28-10 demonstrate the effectiveness of RAAT in improving the trade-off beyond four common baselines and a total of 14 related state-of-the-art (SOTA) works.

Fast Adversarial Training (FAT) has attracted significant attention due to its efficiency in enhancing neural network robustness against adversarial attacks. However, FAT is prone to catastrophic overfitting (CO), wherein models overfit to the specific attack used during training and fail to generalize to others. While existing methods introduce diverse hypotheses and propose various strategies to mitigate CO, a systematic and intuitive explanation of CO remains absent. In this work, we innovatively interpret CO through the lens of backdoor. Through validations on pathway division, diverse feature predictions, and universal class distinguishable triggers in CO, we conceptualize CO as a weak trigger variant of unlearnable tasks, unifying CO, backdoor attacks, and unlearnable tasks under a common theoretical framework. Guided by this, we leverage several backdoor inspired strategies to mitigate CO: (i) Recalibrate CO affected model parameters using vanilla fine tuning, linear probing, or reinitialization-based techniques; (ii) Introduce a weight outlier suppression constraint to regulate abnormal deviations in model weights. Extensive experiments support our interpretation of CO and show the efficacy of the proposed mitigation strategies.

Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations. However, FAT often suffers from catastrophic overfitting (CO), where the model overfits to the training attack and fails to generalize to unseen ones. Moreover, robustness oriented optimization typically leads to notable performance degradation on clean inputs, and such degradation becomes increasingly severe as the perturbation budget grows. In this work, we conduct a comprehensive analysis of how guidance strength affects model performance by modulating perturbation and supervision levels across distinct confidence groups. The findings reveal that low confidence samples are the primary contributors to CO and the robustness accuracy trade off. Building on this insight, we propose a Distribution-aware Dynamic Guidance (DDG) strategy that dynamically adjusts both the perturbation budget and supervision signal. Specifically, DDG scales the perturbation magnitude according to the sample confidence at the ground truth class, thereby guiding samples toward consistent decision boundaries while mitigating the influence of learning spurious correlations. Simultaneously, it dynamically adjusts the supervision signal based on the prediction state of each sample, preventing overemphasis on incorrect signals. To alleviate potential gradient instability arising from dynamic guidance, we further design a weighted regularization constraint. Extensive experiments on standard benchmarks demonstrate that DDG effectively alleviates both CO and the robustness accuracy trade off.

PGD adversarial training, the standard robustness method, can reduce Jacobian Frobenius norm yet worsen clean-input geometry (e.g., TDI 1.336 vs. ERM 1.093). We show this is not an implementation artifact but a theorem-level consequence of supervised learning. We prove that any encoder minimizing supervised loss must retain non-zero sensitivity along directions correlated with training labels, including directions that are nuisance at test time. This holds across proper scoring rules, architectures, and dataset sizes. We call this the geometric blind spot of supervised learning. This theorem unifies four empirical phenomena often treated separately: non-robust features, texture bias, corruption fragility, and the robustness-accuracy tradeoff. It also explains why suppressing sensitivity in one adversarial direction can redistribute sensitivity elsewhere. We introduce Trajectory Deviation Index (TDI), a diagnostic of geometric isotropy. Unlike CKA, intrinsic dimension, or Jacobian Frobenius norm alone, TDI captures the failure mode above. In our experiments, PGD attains low Frobenius norm but high TDI, while PMH attains the lowest TDI with one additional training term and no architectural changes. Across seven tasks, BERT/SST-2, and ImageNet ViT-B/16 (backbone family underlying CLIP/DINO/SAM), the blind spot is measurable and repairable. It appears at foundation-model scale, worsens with model scale and task-specific fine-tuning, and is substantially reduced by PMH. PMH also leads on non-Gaussian corruption types (blur/brightness/contrast) without corruption-specific training.

Fast Adversarial Training (FastAT) seeks to achieve adversarial robustness at a fraction of the computational cost incurred by standard multi-step methods such as PGD-AT. Although numerous FastAT techniques have been proposed in recent years, fair comparison among them remains elusive. Existing benchmarks and public leaderboards typically permit diverse model architectures, varying training configurations, and external data sources, making it unclear whether reported improvements reflect genuine algorithmic advances or merely more favorable experimental conditions. To address this problem, we introduce the FastAT Benchmark, a controlled evaluation framework built on three core design principles: unified architecture requirements, standardized training settings, and strict prohibition of external or synthetic data. The benchmark implements over twenty representative FastAT methods within a single codebase, enabling direct and reproducible comparison. Each method is assessed through a dual-metric evaluation framework that measures both adversarial robustness (accuracy under PGD, AutoAttack, and CR Attack) and computational cost (GPU training time and peak memory footprint). Comprehensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet provide reliable baseline measurements and reveal that well-designed single-step methods can match or surpass PGD-AT robustness at substantially lower cost, while no single method dominates across all evaluation dimensions. The complete benchmark, including source code, configuration files, and experimental results, is publicly available to support transparent and fair evaluation of future FastAT research.

Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulnerable to adversarial examples, much like Convolutional Neural Networks (CNNs). A common empirical defense strategy is adversarial training, yet the theoretical underpinnings of its robustness in ViTs remain largely unexplored. In this work, we present the first theoretical analysis of adversarial training under simplified ViT architectures. We show that, when trained under a signal-to-noise ratio that satisfies a certain condition and within a moderate perturbation budget, adversarial training enables ViTs to achieve nearly zero robust training loss and robust generalization error under certain regimes. Remarkably, this leads to strong generalization even in the presence of overfitting, a phenomenon known as benign overfitting, previously only observed in CNNs (with adversarial training). Experiments on both synthetic and real-world datasets further validate our theoretical findings.

We introduce a self-play framework for semantic equivalence in Haskell, utilizing formal verification to guide adversarial training between a generator and an evaluator. The framework leverages Liquid Haskell proofs for validating equivalence and execution-based counterexamples for inequivalence, organized via a difficulty-aware curriculum. To facilitate this, we release OpInstruct-HSx, a synthetic dataset of $\approx$28k validated Haskell programs. Empirical experiments show that our evaluator transfers effectively to downstream tasks, achieving up to 13.3pp accuracy gain on EquiBench and consistent gains on PySecDB. Ablation studies on the SEQ-SINQ regimes indicate that while inequivalence supervision provides data volume, equivalence proofs are uniquely responsible for the model's reasoning capabilities. The entire training pipeline and dataset are publicly released on GitHub and Hugging Face respectively.

Neural operators have emerged as fast surrogate models for physics simulations, yet they remain acutely vulnerable to adversarial perturbations, a critical liability for safety-critical digital twin deployments. We present a synergistic defense that combines active learning-based data generation with an input denoising architecture. The active learning component adaptively probes model weaknesses using differential evolution attacks, then generates targeted training data at discovered vulnerability locations while an adaptive smooth-ratio safeguard preserves baseline accuracy. The input denoising component augments the operator architecture with a learnable bottleneck that filters adversarial noise while retaining physics-relevant features. On the viscous Burgers' equation benchmark, the combined approach achieves a 2.04% combined error (1.21% baseline + 0.83% robustness), representing an 87% reduction relative to standard training (15.42% combined) and outperforming both active learning alone (3.42%) and input denoising alone (5.22%). More broadly, our results, combined with cross-architecture vulnerability analysis from prior work, suggest that optimal training data for neural operators is architecture-dependent: because different architectures concentrate sensitivity in distinct input subspaces, uniform sampling cannot adequately cover the vulnerability landscape of all models. These findings have potential implications for the deployment of neural operators in safety-critical energy systems including nuclear reactor monitoring.

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that searches for adversarial inputs within the continuous embedding space of LLMs during AT. While CAT has achieved empirical success, its underlying mechanism, i.e., why adversarial perturbations in the embedding space can help LLMs defend against jailbreak prompts synthesized in the input token space, remains unknown. This paper presents the first theoretical analysis of CAT on LLMs based on in-context learning (ICL) theory. For linear transformers trained with adversarial examples from the embedding space on in-context linear regression tasks, we prove a robust generalization bound that has a negative correlation with the perturbation radius in the embedding space. This clearly explains why CAT can defend against jailbreak prompts from the LLM's token space. Further, the robust bound shows that the robustness of an adversarially trained LLM is closely related to the singular values of its embedding matrix. Based on this, we propose to improve LLM CAT by introducing an additional regularization term, which depends on singular values of the LLM's embedding matrix, into the objective function of CAT. Experiments on real-world LLMs demonstrate that our method can help LLMs achieve a better jailbreak robustness-utility tradeoff. The code is available at https://github.com/fshp971/continuous-adv-icl.

Vision Transformer (ViT) models have achieved remarkable performance across various vision tasks, with scalability being a key advantage when applied to large datasets. This scalability enables ViT models to exhibit strong generalization capabilities. However, as the number of parameters increases, the robustness of ViT models to adversarial examples does not scale proportionally. Adversarial training (AT), one of the most effective methods for enhancing robustness, typically requires fine-tuning the entire model, leading to prohibitively high computational costs, especially for large ViT architectures. In this paper, we aim to robustly fine-tune only a small subset of parameters to achieve robustness comparable to standard AT. To accomplish this, we introduce Criticality-Aware Adversarial Training (CAAT), a novel method that adaptively allocates resources to the most robustness-critical parameters, fine-tuning only selected modules. Specifically, CAAT efficiently identifies parameters that contribute most to adversarial robustness. It then leverages parameter-efficient fine-tuning (PEFT) to robustly adjust weight matrices where the number of critical parameters exceeds a predefined threshold. CAAT exhibits favorable generalization when scaled to larger vision transformer architectures, potentially paving the way for adversarial training at scale, e.g, compared with plain adversarial training, CAAT incurs only a 4.3% decrease in adversarial robustness while tuning approximately 6% of its parameters. Extensive experiments on three widely used adversarial learning datasets demonstrate that CAAT outperforms state-of-the-art lightweight AT methods with fewer trainable parameters.

In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality fake images, posing a serious challenge to information authenticity and credibility. Existing generated image detection methods typically enhance generalization through model architecture or network design. However, their generalization performance remains susceptible to data bias, as the training data may drive models to fit specific generative patterns and content rather than the common features shared by images from different generative models (asymmetric bias learning). To address this issue, we propose a Multi-dimensional Adversarial Feature Learning (MAFL) framework. The framework adopts a pretrained multimodal image encoder as the feature extraction backbone, constructs a real-fake feature learning network, and designs an adversarial bias-learning branch equipped with a multi-dimensional adversarial loss, forming an adversarial training mechanism between authenticity-discriminative feature learning and bias feature learning. By suppressing generation-pattern and content biases, MAFL guides the model to focus on the generative features shared across different generative models, thereby effectively capturing the fundamental differences between real and generated images, enhancing cross-model generalization, and substantially reducing the reliance on large-scale training data. Through extensive experimental validation, our method outperforms existing state-of-the-art approaches by 10.89% in accuracy and 8.57% in Average Precision (AP). Notably, even when trained with only 320 images, it can still achieve over 80% detection accuracy on public datasets.

The push for efficient text to image synthesis has moved the field toward one step sampling, yet existing methods still face a three way tradeoff among fidelity, inference speed, and training efficiency. Approaches that rely on external discriminators can sharpen one step performance, but they often introduce training instability, high GPU memory overhead, and slow convergence, which complicates scaling and parameter efficient tuning. In contrast, regression based distillation and consistency objectives are easier to optimize, but they typically lose fine details when constrained to a single step. We present APEX, built on a key theoretical insight: adversarial correction signals can be extracted endogenously from a flow model through condition shifting. Using a transformation creates a shifted condition branch whose velocity field serves as an independent estimator of the model's current generation distribution, yielding a gradient that is provably GAN aligned, replacing the sample dependent discriminator terms that cause gradient vanishing. This discriminator free design is architecture preserving, making APEX a plug and play framework compatible with both full parameter and LoRA based tuning. Empirically, our 0.6B model surpasses FLUX-Schnell 12B (20$\times$ more parameters) in one step quality. With LoRA tuning on Qwen-Image 20B, APEX reaches a GenEval score of 0.89 at NFE=1 in 6 hours, surpassing the original 50-step teacher (0.87) and providing a 15.33$\times$ inference speedup. Code is available https://github.com/LINs-lab/APEX.

Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While this paradigm has proven effective for improving clean accuracy on the target domain, adversarial robustness has received far less attention, especially when the original pretrained model is not explicitly designed to be robust. This raises a practical question: can a pretrained, non-robust model be adapted at test-time to improve adversarial robustness on a target distribution? To face this question, this work studies how adversarial training strategies behave when integrated into adaptation schemes for the unsupervised test-time setting, where only a small set of unlabeled target samples is available. It first analyzes how classical adversarial training formulations can be extended to this scenario, showing that straightforward distillation-based adaptations remain unstable and highly sensitive to hyperparameter tuning, particularly when the teacher itself is non-robust. To address these limitations, the work proposes a label-free framework that uses the predictions of a non-robust teacher model as a semantic anchor for both the clean and adversarial objectives during adaptation. We further provide theoretical insights showing that our formulation yields a more stable alternative to the self-consistency-based regularization commonly used in classical adversarial training. Experiments evaluate the proposed approach on CIFAR-10 and ImageNet under induced photometric transformations. The results support the theoretical insights by showing that the proposed approach achieves improved optimization stability, lower sensitivity to parameter choices, and a better robustness-accuracy trade-off than existing baselines in this post-deployment test-time setting.