Adversarial Training

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.

We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluate and improve the robustness of our production systems. To this end, we use it to adversarially train GPT-5.6, our most robust model to prompt injections to date. To create GPT-Red, we design a scalable self-play algorithm where the model is tasked with attacking a diverse population of simultaneously-trained defender agents. We train the model on realistic red-teaming environments using compute on the same scale as some of our largest RL post-training runs, making it the single-largest LLM safety training run ever documented. GPT-Red excels at red-teaming: it reliably breaks our past models up to GPT-5.5, it finds more successful attacks than human red-teamers, and it generalizes to held-out environments, defender models, and harnesses. In the future, we expect that as we improve the robustness of each new GPT model, it will in turn will provide better learning signal for \textit{even stronger} red-teamer agents, thus unlocking a self-improvement flywheel.

The emergence of the recent outstanding capabilities of Arabic Language Models has opened doors for exposing their vulnerabilities. One of the major security risks associated with such Natural Language Processing models is adversarial attacks. These attacks can deceive the model into the wrong prediction, raising critical model security and safety concerns. This study aims to assess the robustness of five state-of-the-art Arabic Language Models under a distinct set of Arabic adversarial attacks applied at various levels of granularity and using different example generation strategies. We also explore a defense technique based on adversarial training to enhance model robustness. The results show that insertion of diacritics can reduce the accuracy of some models by 92% while maintaining a low perturbation distance. For word-level attacks, manipulating Arabic conjunctions preserves high semantic similarity scores, low perturbation distance, and leads to an accuracy degradation of up to 58%. For sentence-level attacks, paraphrasing proves its effectiveness by an average reduction of 76% in the victim models' performance. While adversarial training improves overall resilience, with MARBERT being the most robust and AraBERT showing the greatest relative gains, challenges persist, particularly against character-level noise. These findings highlight both the potential and limitations of current defense strategies in morphologically rich languages like Arabic.

AI-enabled visual perception systems are increasingly deployed in intelligent transportation infrastructure and autonomous vehicle related applications. However, physically realizable adversarial appearances pose a significant reliability challenge for these safety-critical systems. Adversarial training is effective, but repeated co-occurrence between adversarial texture and positive person instances can cause detectors to treat the texture itself as evidence of object presence, forming a patch texture shortcut. The detector may then treat texture as evidence for the target, causing false detections on texture-only inputs and weakening cross attack generalisation. We propose InsCAT, an instance-level contrastive adversarial training framework that prevents detectors from using adversarial texture as an independent decision cue. SICA aligns adversarial person features with matched clean features and separates them from texture-only negatives, while ROPO and Guard maintain online attack pressure and coordinate training. We evaluate eight independently generated attack textures on rendered nuScenes, INRIAPerson, printed garments, and three detector families. InsCAT achieves an average attack AP of 82.3% on rendered nuScenes, exceeding the strongest baseline by 11.1 points.Relative to AT-Mix, texture FPR decreases from 46.9% to 7.3%. Physical tests yield an F1 score of 96.6% and an FPR of 1.8%. Consistent gains across separately trained detectors demonstrate applicability across architectures with direct inference. The findings show that robust physical detection depends on preserving target related evidence while preventing adversarial texture from becoming an independent decision cu

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.

We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard. While adversarial fine-tuning trivially closes the 2025 winning evasion recipes, we uncover a fundamental asymmetry in detector vulnerability: pushing generated text out of the detector's training distribution reliably defeats adversarial detection, whereas pulling it into the distribution (e.g., mimicking human training data) fails completely. Exploiting this, we introduce two novel out-of-distribution attack families - cross-decade register attacks and modernist stream-of-consciousness form. Both strategies easily bypass adversarial closure, achieving up to approximately 50x higher fool rates than previous methods while preserving naturalness. Furthermore, experiments show that the obvious deployer countermeasure (augmenting training data with period prose) fails to close the vulnerability. Our findings show that the tested detector families, including adversarially fine-tuned ones, exhibit persistent vulnerabilities under structural out-of-distribution shifts, a mechanism that directly powers our leading competition performance.

Adversarial robustness research has produced hundreds of defended models over the past decade, yet the literature almost universally reports robustness results in isolation: standard (clean) accuracy and adversarial accuracy of the robust model are shown, but the gap to the corresponding vanilla model is rarely quantified. We introduce VanillaBench, a systematic benchmark that makes this gap explicit. For every adversarially-trained model catalogued by RobustBench across four threat models, we compute the accuracy difference against multiple vanilla references from Papers with Code, computed over both all entries and no-extra-data entries, the best vanilla model as of the robust model's publication year, and an architecture-matched baseline. Across all 186 robust models, the mean delta clean relative to the best vanilla model ranges from -7.7 to -29.5 percentage points, and even the single most robust model per track still trails its temporal vanilla counterpart by 4.0-21.0 points. The architecture-matched comparison, which isolates the effect of adversarial training from architectural differences, reveals a mean gap of -3.5 to -17.5 points. Restricting this architecture-matched comparison to models whose vanilla accuracy is known for the exact same architecture, rather than approximated from a related one, narrows the gap to -4.0 to -14.0 points. These results demonstrate that the robustness-accuracy trade-off is substantially larger than what is typically conveyed by individual papers. This information is critical for practitioners and decision-makers. When deploying models in real-world settings, the accuracy cost of robustness directly affects business outcomes, yet current publications do not provide the vanilla baseline needed to assess it. We argue that future robustness evaluations should report vanilla-referenced accuracy gaps as a standard component.

In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks. We show that extensive exposure can persist without rote memorization and is instead caused by a tunable connection to adversarial robustness. We begin by presenting three surprising results: (1) recent defenses that inhibit reconstruction by Model Inversion Attacks (MIAs), which evaluate leakage under an idealized attacker, do not reduce standard measures of information dependency (HSIC); (2) models that maximally memorize their training datasets remain robust to MIA reconstruction; and (3) models trained without seeing 97% of the training pixels, where recent information-theoretic bounds give arbitrarily strong privacy guarantees under standard assumptions, can still be devastatingly reconstructed by MIA. To explain these findings, we provide causal evidence that privacy under MIA arises from what the adversarial examples literature calls ``non-robust'' features (generalizable but imperceptible and unstable features). We further show that recent MIA defenses obtain their privacy improvements by unintentionally shifting models toward such features. To establish this causal relationship, we introduce Anti Adversarial Training (AT-AT), a training regime that intentionally learns non-robust features to obtain both superior reconstruction defense and higher accuracy than state-of-the-art defenses. Our results revise the prevailing understanding of training data exposure and reveal a new privacy-robustness tradeoff.

Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data. Although adversarial training offers a feasible solution, existing methods often rely on external scenario generators, heuristic perturbations, or simulator-heavy rollouts, which makes them difficult to integrate with modern autoregressive planners. Here, we cast adversarially robust planner learning as a constrained min-max game and propose Adversarial World Modeling (AWM), a theoretically grounded multi-agent self-play fine-tuning framework. Since solving the exact game is intractable, AWM introduces a principled decoupled solver. In the inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions via counterfactual credit assignment. In the outer maximization, the ego planner optimizes a regret-aware robust best response against the frozen AWM, utilizing tail-risk weighting and reference-anchored trust regions to improve hard-case recovery while preserving nominal driving behavior. Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions and yields a robust planner that achieves competitive closed-loop performance in both nominal and highly interactive long-tail scenarios. Theoretical analysis justifies the decoupled solver and the main optimization components.

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.

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.

Sparse feature selection is critical for high-dimensional machine learning, yet traditional $\ell_1$-regularized methods are often brittle under observational noise and spurious correlations, leading to unstable feature supports and degraded generalization. Although adversarial training has been widely used to improve model robustness, its interaction with hierarchical sparse feature selection remains underexplored. In this work, we propose Adversarial LassoNet (AdLNet), a stability-driven sparse feature selection framework that integrates input-space adversarial perturbations with the hierarchical sparsity mechanism of LassoNet. We derive a tractable first-order adversarial approximation under local smoothness assumptions and provide an NTK-inspired spectral analysis to characterize how perturbation-driven training can reduce gradient concentration. Experiments on high-dimensional SERS data, six public benchmark datasets, and ColoredMNIST show that AdLNet maintains competitive sparse-selection performance while improving out-of-distribution robustness by 4.4% and feature support reproducibility by 6.3% under nearly matched support sparsity on ColoredMNIST. On the high-dimensional lung cancer screening dataset, AdLNet achieves a 5.3% test accuracy gain and a 6.0% AUC improvement over vanilla LassoNet. Code and dataset are available at https://github.com/719573/Adversarial-LassoNet.

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.

In this paper, we propose Adversarial Dynamics Priors (ADP) for perturbation-resilient humanoid locomotion control. Existing motion prior-based methods induce natural motion styles by imitating kinematic motion features, but they do not directly regularize dynamics features, such as CoM motion, centroidal momentum, contact forces, and contact states. To address this limitation, we replace kinematic motion-style feature with selected dynamics features extracted from locomotion trajectories as the target of adversarial regularization. To this end, we use trajectory optimization to construct a reference dataset and train a discriminator to evaluate whether policy-induced temporal windows are consistent with the resulting reference distribution. Without explicit motion tracking, ADP encourages policy rollouts to remain close to the reference support, even after perturbations. Experimental results show that, compared with AMP, the strongest baseline in our evaluation, ADP improves the $80\%$-success impulse threshold ($J_{80}$) by $16.7\%$, while reducing direction-averaged recovery time and velocity tracking error by $47.9\%$ and $35.4\%$, respectively.

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.

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.

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.

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.

The vulnerability of ML models to adversarial examples has recently emerged as a major concern. While adversarial training is one of the most effective countermeasures to this issue, its high computational cost remains an obstacle to practical deployment. Recent progress in reducing this cost has relied, in the case of linear models, on a formal equivalence between the adversarial risk and a simpler form of regularized risk. This enabled significantly more efficient training procedures, which naturally raises the question of whether such an equivalence can be extended beyond linear models. In this work, we formally show that no such equivalence is possible for two-layer networks. Our proofs proceed via a reduction to key properties that fundamentally separate the adversarial risk from any simple regularized risk which would only exhibit a weak form of data dependence. Beyond this setting, we provide empirical evidence on Wide-ResNets indicating that the same type of impossibility persists in deeper and more expressive architectures.

In this work, we introduce a training procedure for shallow neural networks that promotes robustness against adversarial attacks. We solve a non-convex Lipschitz-regularized training program by introducing a convex restriction that can be efficiently solved to global optimality. Our approach can be employed as a post-processing step by taking a pre-trained network as an initial solution to then solving the convex program whose optimal network is guaranteed to be no worse than the initial one. We illustrate the improvements of our training procedure with experiments using real world datasets for regression tasks under an adversarial setting. We show numerically that solving our proposed convex program yields networks with lower objective values on the Lipschitz-regularized program compared to existing methods. Additionally, we show that on certain datasets, networks obtained using our convex training program are both more accurate and robust with respect to adversarial attacks.

We present Veriphi, a GPU-accelerated neural network verification system that combines fast adversarial attacks with formal bound certification using alpha,beta-CROWN methods. Through systematic experiments on MNIST and CIFAR-10 using three training methodologies (standard, adversarial, certified), we demonstrate that training method effectiveness is fundamentally dataset-dependent. Interval Bound Propagation (IBP) achieves 78% certified accuracy on simple MNIST (784 dimensions) but provides negligible certification performance on the more complex CIFAR-10 dataset, where PGD adversarial training dominates with 94% certification at small perturbations. We achieve 5x verification speedup through attack-guided falsification and scale our approach to production-size models (105.8M parameters) for real-world aerospace logistics optimization. Our results challenge the assumption that certified training universally outperforms adversarial training, showing context matters critically for verification strategy selection.

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.

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.

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense. In this work, we trace this collapse to two failure modes. First, existing defense methods are confined to recognizing specific attack patterns, rather than assessing whether the intent of every embedded instruction is relevant to the user task. Second, training-based defenses, which otherwise offer the strongest safety-utility trade-off, assemble their adversarial examples from a handful of hand-crafted templates, and the resulting defender fails to generalize outside that narrow strategy distribution. To address these gaps, we propose RETA, a training-based method that grounds defense decisions on the user tasks rather than attacker-controlled data. At each tool-output step, the defender undertakes chain-of-thought reasoning verifying that its actions are consistent with the user task. Leveraging red-teaming, a simulated attacker synthesizes adversarial training data and receives a dictionary-learning diversity reward, achieving broad coverage of injection-reformulation strategies. Together, these allow the defender to be optimized via multi-objective reinforcement learning and achieve better safety-utility trade-off. Across six black-box adaptive attacks, RETA keeps every per-attack ASR below 10%, with average ASR of 2.92% and 3.75% on the two target models, while preserving most utility under attack and on clean inputs.

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.

Despite recent progress in Natural Language Processing (NLP), models remain vulnerable to word substitution attacks. Most existing defenses focus on first order sensitivity and measure how much the output changes when the input is slightly perturbed. However, they ignore how this sensitivity evolves, which is described by curvature. When gradients vary sharply, models can still fail. This paper introduces the Smooth Growth Bound Tensor (S-GBT), a second order method that bounds the Hessian element-wise, for which we provide formal theoretical proofs on the resulting robustness bounds. A regularization term is added during training to minimize these bounds. This yields tighter certified robustness against word substitution attacks. The change in the output under word substitution is bounded by both a linear term and a quadratic term. S-GBT is derived for two architectures: Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). The method is integrated directly into the training objective. Its effectiveness is evaluated on multiple benchmark datasets. The results show that combining first and second order regularization improves certified robust accuracy by up to 23.4% compared to prior methods, while clean accuracy remains competitive. These findings indicate that controlling both the gradient and its variation is a promising direction for building more robust models.

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.

Parameter-Efficient Fine-Tuning (PEFT) has become essential for adapting foundation models to downstream NLP tasks. However, current PEFT methods often struggle with robustness to noise and performance degradation on limited training data. We propose SDBN (Small Data Big Noise), a unified framework that brings adversarial training to PEFT - a combination that remains less studied in the PEFT setting despite its complementary strengths - to enhance model robustness and generalization, outperforming alternative approaches. We also introduce two variants of the method that use discrete uncertainty sets: SDBN-h, which enumerates character-level edits and selects worst-case variants using gradients, and SDBN-p, which uses LLM-generated variants for robust optimization in generative tasks. Experiments across multiple benchmarks reveal substantial improvements, particularly in low-resource settings and under both word-level and character-level corruptions. This framework addresses the less explored intersection of adversarial training and parameter-efficient adaptation, without introducing additional parameters or only modest computational overhead, making PEFT deployments more reliable in real-world scenarios where data scarcity and linguistic variability often coexist