Overview

Adversarial robustness asks whether a model still predicts or acts reliably when an attacker makes small, strategic changes to its inputs, training data, or operating environment. Common approaches include adversarial training, which exposes models to attacks during learning; randomized smoothing and other certification methods, which provide conditional guarantees; and input purification, representation regularization, and test-time adaptation. Evaluations span image classifiers and detectors, language and multimodal models, graphs, time series, and safety-critical systems, using both empirical attacks and formal bounds. A central tension is that gains can depend on the attack, data, and deployment setting, while stronger robustness may cost clean accuracy or compute; adaptive, realistic evaluation and guarantees that match real threats remain open challenges.

Latest papers

509 papers35 papers in the last four weeks, down 34% on the four weeks before. 0.3% of all new papers.

Oct 22, 2026

Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis

Financial transaction networks are naturally represented as multigraphs, where repeated transactions between the same pair of accounts are modeled as distinct edges. Recently proposed multigraph neural network architectures leverage this structure explicitly to achieve a strong performance on anti-money laundering (AML) tasks. However, their robustness to adversaries that manipulate transaction structures to evade detection remains largely unexplored. We present the first scalable framework for structural attacks and adversarial training of multigraph neural networks using node-edge incidence matrices, adapting projected gradient descent and projected randomized block coordinate descent methods to optimize structural perturbations over such matrices. We further introduce a cycle-based regularizer that penalizes changes in the global counts of directed 2- and 3-cycles, providing a structural measure of attack plausibility. Experiments on synthetic pattern-detection and realistic AML datasets show that our learned attacks substantially outperform non-learnable perturbation baselines in reducing detection performance (PR-AUC), while adversarial training consistently improves robustness against these attacks. These results demonstrate that multigraph neural networks are vulnerable to learned structural attacks and that adversarial training provides an effective defense. Our code is available at https://github.com/denheijmans/robust_multignn.
Oct 21, 2026

ExGrad: Beyond Suppression - Explicit Clean-Gradient Subtraction in Adversarial Training

Adversarial training derives updates from surrogate losses, but source-loss descent does not directly characterize an update's effect on adversarial margins. We introduce ExGrad (extrapolative gradient recomposition), which constructs clean-input, adversarial-input, and adversarial-weight-perturbed (AWP) gradients. Virtual steps measure their margin responses, and a globally solvable three-variable problem selects coefficients over a bounded affine domain without nonnegativity constraints. Across affine radii on CIFAR-10, negative clean coefficients rapidly predominate and increase in magnitude with the radius. Cross-zero interventions show that setting the clean coefficient to zero is insufficient: mild subtraction improves PGD-20, while stronger subtraction trades clean accuracy for further PGD-20 gains. In CIFAR-10 WRN-28-4 controls, none of the three candidate-removal variants matches full ExGrad. Projection diagnostics show that negative clean coefficients usually coexist with positive net clean-axis projections, although both decrease as the radius grows. Norm-matched controls indicate that update magnitude alone does not explain the moderate-radius gains. Experiments on CIFAR-10, CIFAR-100, and ImageNet-100 show radius-dependent improvements over AWP. On CIFAR-100, ExGrad at R=0.8R=0.8 improves all five reported metrics, including clean and AutoAttack accuracy by 3.84 and 1.75 percentage points. On ImageNet-100, the same radius improves all four robust metrics over both AWP and PGD-AT. These results identify clean-gradient subtraction as a response-revealed update preference whose strength and clean-robust operating point are controlled by the affine radius.
Oct 20, 2026

Learning-Theoretic Foundation for General Coded Computing: The Adversarial Setting

Adversarial workers pose a severe challenge in distributed computing systems by returning corrupted outputs that can substantially distort the recovered computations. Coded computing addresses this threat by introducing redundancy across worker assignments. Existing exact and approximate coded-computing methods typically handle adversarial outputs by explicitly locating and correcting or removing erroneous evaluations, which adds significant computational overhead at the master node. Moreover, existing analyses do not characterize how the recovery error scales with the number of workers and the adversarial budget. In this paper, we develop an adversarially robust extension of general coded computing (GCC), a learning-theoretic approximate coded-computing framework that designs the encoder and decoder by minimizing an upper bound on the end-to-end recovery error. Rather than identifying corrupted workers, the proposed method uses smoothness regularization to limit the influence of their outputs. The resulting encoder and decoder can be implemented using smoothing splines with linear master-side complexity. We derive a non-asymptotic bound on the worst-case end-to-end approximation error by decomposing it into three components: (1) the encoder approximation error, (2) the decoder reconstruction error under fully honest results, and (3) the adversarial perturbation error. For maximum of q≥1q\geq 1 adversarial workers among NN workers results in a worst-case error of order O((q/N)6/5)\mathcal{O}((q/N)^{6/5}) with appropriate selection of smoothness parameter, demonstrating that the approximation error vanishes asymptotically whenever the number of adversaries grows sublinearly with the network size. Experiments on scalar computation and neural-network inference are consistent with the predicted convergence behavior.
Oct 19, 2026

Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness

Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training pipelines, distillation methods, and data. These shared algorithmic choices can expose an otherwise distinct model ecosystem to concentrated risks leading to a vulnerability monoculture. Yet current practice in assessing adversarial robustness is restricted to individual robustness scores and attack transfer rates, leaving open the unexplored fundamental question: how many attacks suffice for catastrophic widespread compromise? In this paper, we investigate the empirical nature of shared vulnerabilities within a model pool and introduce Systemic Adversarial Robustness (SAR), a novel measure of shared vulnerability of a model pool through the attack diversity needed to exploit it. Specifically, SAR interpolates between single-attack transferability and independent per-model robustness: small values reveal a vulnerability monoculture, whereas large values indicate that failures are dispersed across models. We theoretically formulate SAR as a partial set-cover problem with provable approximation guarantees---enabling the development of scalable algorithms to empirically measure the systemic adversarial robustness. We empirically test the shared vulnerability of vision and large language models and characterize their shared collective vulnerability curve. Specifically, we demonstrate that model pools distilled from DeepSeek-R1 and Claude Opus 4.6 exhibit lower estimated systemic robustness than their corresponding parent pools, revealing a potential systemic cost of frontier-model distillation. Our framework seeks to establish vulnerability monoculture as a measurable target for a more wholistic adversarial evaluation of model populations.
Oct 19, 2026

Language Guidance for Supervised Vision Training: An Empirical Study of Generalization

Deep neural networks have achieved remarkable success on vision benchmarks, yet they continue to struggle with many generalization challenges. Supervised vision training relies on one-hot labels, which provide limited information about semantic structure and shared attributes between classes. This limited supervision can leave visual representations vulnerable to distribution shifts, spurious correlations, texture bias, adversarial perturbations, and forgetting in sequential learning settings. We study whether pretrained language models can serve as lightweight auxiliary supervision for vision training without requiring paired image-text data, prompt engineering, or contrastive objectives. Specifically, we evaluate two forms of language guidance, Explicit Language Guidance (ExLG) and Implicit Language Guidance (ImLG). We conduct a comprehensive evaluation across six generalization regimes, including in-distribution, out-of-distribution generalization, shortcut and spurious correlation resistance, texture and shape bias, adversarial robustness, and continual learning. Our analyses show that the two mechanisms have complementary strengths, with explicit guidance consistently benefiting in-distribution, low-data performance, and continual learning retention, while implicit guidance is often more useful in shortcut-sensitive settings and under stronger adversarial perturbations. Importantly, both are lightweight and add minimal parameters and training overhead. The analyses characterize when language-derived structure helps supervised vision training and provides a practical roadmap for using off-the-shelf pretrained models from another modality as auxiliary supervision.
Oct 19, 2026

Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devices

Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared to cloud-based deployment. However, on-device models embedded in mobile applications can be unpacked and exposed to adversaries, enabling cross-node attacks in centrally distributed ecosystems, where adversarial examples crafted on one compromised device transfer effectively to other nodes sharing the same models. To address this threat, we propose VeilNN, a defense framework that reduces adversarial transferability across on-device models via model obfuscation. The core idea of VeilNN is to introduce controlled model diversity while preserving original task functionality. Specifically, VeilNN applies stealthy and irreversible obfuscation at both the architectural and parameter levels through network cell obfuscation and layer assembling, and is applicable to diverse NN architectures, including MLPs, CNNs, and Vision Transformers. Extensive experiments demonstrate that VeilNN effectively defends against cross-node attacks, achieving an average defense success of 49.19% and up to 81.19% across four adversarial attack types, with more than 33.16% improvement over existing defenses.
Oct 19, 2026

Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attack

With the advancement of powerful AI chips, on-device machine learning is gaining traction for its low latency and privacy protection. However, when edge devices are compromised, attackers can obtain white-box access to the deployed models by reversing the apps directly to obtain the knowledge of peer devices, which is known as Cross-Node Attacks, like performing efficient adversarial attacks. Most existing defenses target known vulnerabilities, yet white-box access still enables attackers to uncover more unknown weaknesses. This creates a critical risk for edge-device deployments, where one compromised device can endanger all models distributed from the same source. Motivated by findings that the model robustness is primarily influenced by the curvature of the decision boundary, we investigate how model parameters shape its curvature. In this paper, we propose a novel method, BMO, that obfuscates model parameters to diversify the decision boundary further resisting cross-node attack while preserving its benign accuracy. Specifically, we explore decomposing model parameters into boundary-position and boundary-curvature components based on null-space constraints, then models with differentiated decision boundaries are instantiated by injecting noise into the boundary-curvature component. Across all four major types of adversarial attacks with four widely-deployed on-device models, BMO achieves an average success rate of 68.68% in defense, far exceeding the most competitive baseline, which attains only 22.32% in defending against cross-node attacks. Moreover, BMO achieves comparable performance in benign accuracy compared with baselines.
Oct 18, 2026

Robust Direct Preference Optimization under Preference Label-Flip Attacks

Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipulated by adversarial preference label flip attacks, which are specifically designed to mislead the learner toward an attacker-chosen target policy. To address this issue, we design robust DPO methods that can defend against such attacks. Building on the property that lable flips induce parameter-independent gradient shifts in log-linear DPO, we propose Trim-KK Robust-DPO, which removes the KK highest-impact pairs, and Soft-Trim-KK Robust-DPO, which smoothly downweights them. We establish deterministic gradient perturbation bounds uniformly over all attack sets containing at most KK flips, explicitly separating defense-induced bias from surviving attack effects. Under bounded-region assumptions, these bounds yield time-uniform parameter and policy deviation guarantees. We further quantify how quadratic regularization improves curvature while introducing additional bias. Experiments on Stanford Human Preferences, HH-RLHF, and UltraFeedback-Binarized validate our analysis.
Oct 16, 2026

On the tradeoff between robustness and geometric accuracy in adversarial training

For non-parametric binary classification in the presence of an adversary, we prove an optimal quantitative estimate for adversarial classifiers controlling geometric accuracy, as measured by the Hausdorff distance to the Bayes classifier, in terms or their robustness, as encoded by the adversarial budget ε\varepsilon. This rigorously shows that robust classifiers sacrifice at most O(ε)O(\sqrt{\varepsilon}) or O(ε)O(\varepsilon) in accuracy, depending on the regularity of the underlying Bayes classifier. In contrast to prior work on the incompatibility of robustness and accuracy over low-complexity hypothesis classes, our work shows that high-complexity hypothesis classes allow for robust classifiers with precisely quantified accuracy. Our results apply for adversaries determined by any norm on Euclidean space and in both the infinite and finite data settings.
Oct 14, 2026

ACR-Net: Mitigating Semantic Dominance via Contrastive Acoustic-Semantic Decoupling

Speech Emotion Recognition (SER) models and Audio LLMs fail when vocal tone contradicts textual semantics. Extensive training on congruent data engenders a rigid semantic prior, causing "Semantic Dominance", a severe text bias during cross-modal conflicts. We introduce the ASPIRE benchmark of adversarial audio-text pairs across four conflict types, alongside two metrics: Semantic Overconfidence Penalty (SOP) and Latent Decoupling Degree (LDD). Unlike fusion methods that merely re-weight collapsed features, our Acoustic Conflict Resolution Network (ACR-Net) uses Cross-Modal Attention and Contrastive Decoupling Loss to disentangle contradictory representations into orthogonal latent spaces. Experiments show existing models fail under polarity conflicts due to extreme semantic overconfidence. Conversely, ACR-Net preserves acoustic fidelity, maintaining high LDD to drive SOP near zero, achieving superior Acoustic Accuracy (ACC) in both adversarial and standard scenarios.
Oct 14, 2026

CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation

Adversarial robustness distillation typically treats a robust teacher as a fixed knowledge source and transfers robustness to a compact student in a one-way manner. This paradigm terminates teacher-student interaction once the student is distilled, thereby discarding potentially useful feedback from the distilled student. However, exploiting such feedback is nontrivial because indiscriminate weak-to-strong transfer may propagate student errors to the teacher. To address this issue, we propose Cyclic Adversarial Robustness Distillation (CARD), a closed-loop framework that turns the distilled student into a feedback source for refining the robust teacher and subsequently transfers the teacher gains back to the same student. CARD first performs strong-to-weak adversarial distillation and then uses reliability-enhanced student feedback to refine the robust teacher. The refinement combines inverse adversarial student feedback with teacher-student discrepancy maximization, after which the refined teacher is used to continue training the same student under the unchanged base distillation objective. We further establish a sample-level sufficient condition for reliable weak-to-strong feedback transfer and derive a distribution-level upper bound on the refined teacher's risk. Experiments on CIFAR-10, CIFAR-100, and TinyImageNet-10 across multiple teacher-student architectures and base distillation methods show that CARD improves adversarial robustness in most evaluated settings while generally preserving clean accuracy. These results show that the distilled student can provide useful feedback to the teacher, enabling robustness transfer to proceed beyond the conventional one-way teacher-to-student paradigm.
Oct 14, 2026

No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation

Recent advances in diffusion models have enabled high-fidelity, identity-preserving image generation for personalized applications such as digital avatars and virtual try-on systems. However, their reliance on sensitive facial reference images raises growing privacy concerns. Existing defense mechanisms are primarily designed for training-based personalization and struggle to generalize to emerging training-free approaches, due to fundamental differences in their identity integration paradigms. To bridge this gap, we propose IDGuardian-the first generalizable and model-agnostic identity protection framework capable of defending against both training-based and training-free personalization methods. IDGuardian abstracts the personalization process into two critical stages: identity extraction and identity injection. It then introduces crafted adversarial perturbations to simultaneously disrupt both stages. Specifically, it degrades the identity features extracted by external encoders and establishes an adversarial conceptual bridge that misdirects the generative trajectory away from the target identity. Extensive experiments show that IDGuardian effectively protects identity across various personalization pipelines and model architectures, while remaining robust to post-processing, adaptive attacks, and cross-dataset generalization. Our code is available at https://github.com/OpenAscent-L/IDGuardian.git.
Oct 13, 2026

DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision

Emerging decision models such as JEV provide typed interfaces that map task instructions and observations directly to choices, judgments, and scores. As these models are increasingly used for automated decision-making, understanding their reliability under adversarial manipulation becomes critical. We introduce DecisionRobust, a benchmark for systematically evaluating the robustness of decision models across textual and visual inputs. Our benchmark covers practical decision-making scenarios and a diverse suite of attacks, including semantics-preserving text perturbations, image perturbations, and prompt injection in both modalities. We curate evaluation sets through external validity checks and cross-model candidate selection. We evaluate 30 model configurations on text tasks and 17 on vision tasks, including 24 and 12 held-out models, respectively, that are excluded from candidate selection. Our experiments reveal several key findings. First, attacks expose vulnerabilities beyond the models used for construction and selection, although optimized image perturbations transfer weakly to many targets even with multiple surrogates. Second, relative model robustness varies across tasks and attack types, and resistance to input perturbations does not necessarily imply resistance to prompt injection. Third, label-consistency checks substantially reduce measured attack success across text and image settings, highlighting the importance of validating apparent failures. The benchmark is available at https://yifan-lan.github.io/DecisionRobust/.
Oct 12, 2026

Mitigating Black-Box Score-Based Query Attacks via Gradient Confusion

Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repeated model queries to craft adversarial examples, requiring neither access to model parameters nor architecture. Existing defenses predominantly rely on stochastic output perturbations, which fail to prevent determined attackers from recovering stable gradient estimates by increasing query budgets or averaging over randomness. In this work, we propose the Gradient Confusion Defense (GCD), a retraining-free, deterministic test-time wrapper that actively shapes the probability vector returned to querying adversaries. By solving a constrained optimization problem grounded in the model's Jacobian, GCD aligns the exposed logit-gradient with a target confusion direction that is maximally misaligned with the true adversarial loss gradient---increasing the query complexity of attacks without sacrificing predictive utility or top-1 accuracy. We provide rigorous theoretical analysis demonstrating that GCD provably slows gradient-estimation-based attacks and induces systematic accept/reject errors in random search-based attacks, with the confusion effect amplifying as the fraction of defended queries increases. Extensive experiments on CIFAR-10 and ImageNet across multiple architectures (ResNet-18, ResNet-50, ViT-B/16) and four state-of-the-art attacks confirm these predictions: GCD achieves state-of-the-art robustness, while incurring zero clean accuracy degradation. %Crucially, unlike randomization-based defenses, GCD's deterministic structure provides resilience against adaptive attacks that exploit stochasticity, making it well-suited for security-critical deployment settings.
Oct 12, 2026

Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models

Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection effectiveness, clean fidelity, compatibility, and tamper resistance. We incorporate long-horizon attack simulations to strengthen resistance to protection removal. Experiments with a single protection tool show improved resistance to re-alignment at a cost to clean fidelity, motivating further research toward practical model-side protection.
Oct 12, 2026

Adversarial Robustness of Camera-Radar Sensor Fusion for Autonomous Driving

Autonomous driving (AD) relies on multi-sensor perception to interpret the surrounding environment. However, the robustness of camera--radar fusion under adversarial conditions remains largely unexplored. This paper presents a systematic measurement study of the robustness of camera--radar sensor fusion in AD. We construct a unified evaluation pipeline on the nuScenes dataset that simulates attacks on both sensing modalities, including eight camera-image perturbations and three radar point-cloud perturbations. We evaluate five camera--radar fusion algorithms across two perception tasks, 3D object detection and depth estimation, and quantify their performance under clean and attacked inputs using standard metrics. Our evaluation reveals a clear asymmetry in the robustness of fusion systems. Camera perturbations substantially degrade both object detection and depth estimation, and moderate attack strengths are already sufficient to cause severe performance degradation. In contrast, the evaluated radar perturbations produce smaller and task-dependent effects, with object-detection models showing particularly limited degradation. Our analysis attributes this difference to the strong dependence of existing fusion architectures on dense camera features, together with the filtering, association, and confidence-weighting mechanisms commonly applied to sparse radar measurements. These results demonstrate that sensor fusion does not inherently guarantee robustness and that the contribution and reliability of each sensing modality must be explicitly considered under adversarial conditions. Based on four empirical findings, we derive measurement-guided design implications for future robust camera--radar fusion, including modality-specific reliability estimation, cross-modal consistency checking, adaptive fusion, and graceful failover under severe sensor degradation.
Oct 11, 2026

Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging

Deep learning is now central to radiology, helping detect changes on X-rays, CTs, and MRIs. However, these systems are highly vulnerable to adversarial attacks - small, crafted perturbations that mislead models while appearing unchanged to humans. Such errors risk missed cancers or false positives. Studies show over 90% attack success on medical scans. Almost 30% of US hospitals use AI in imaging in 2023. Thus, an effective method of detecting such attacks and their directionality is crucial to ensure the credibility and reliability of medical systems based on DNNs. We propose a novel detection framework that leverages subsequent attacks using random noise to identify adversarial perturbations. Our approach uses the analysis of variations in the Sigmoid function to distinguish genuine medical images from adversarially manipulated ones. Specifically, we compare prediction differences between clean and attacked images, as well as between different adversarially altered versions, to improve detection accuracy. We evaluated our method on three popular medical datasets including 'Chest X-Ray Images for Classification', 'Retinal Fundus Multi-disease Image Dataset' and 'Brain Tumor Dataset' under various attack scenarios, including random noise. Our framework achieved up to 99.8% ACC in identifying adversarial directional attacks, significantly outperforming existing defense mechanisms. It consistently identified adversarial samples across varying attack strengths while keeping false positives low, showing strong reliability and potential for clinical use. Furthermore, our proposal highlights its potential for real-world deployment.
Oct 11, 2026

Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification

Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certified ℓ2\ell_2 defenses today face a costly trade-off: randomized smoothing (RS) requires hundreds of noisy queries per input, while Lipschitz networks (LN) constrain the architecture and sacrifice clean accuracy. We take a detection-oriented approach instead: rather than certifying that predictions are invariant inside an ℓ2\ell_2 ball, we certify that adversarial inputs within an ℓ2\ell_2 ball are detected --- a guarantee aligned with security-critical deployments where missing an attack is costlier than flagging a clean input. To realize this, we prove a Lipschitz-margin reduction from certified ℓ2\ell_2 robustness to certified detection, which reduces the problem to handling a single Lipschitz constant LL. We introduce two detector families: DAdv\mathbb{D}_{Adv}, which estimates LL from a single defender-side perturbed pair, and Dlc\mathbb{D}_{lc}, which augments that pair with a local margin centroid to keep the estimate above what the certificate requires. Both deploy on any pretrained classifier without retraining. With a valid global bound, the detector is fully certified at that radius; with a local estimate L′L', certification is sample-wise and applies only when our certified condition holds. Across MNIST, CIFAR-10, and ImageNet-1k on four backbones (LeNet-5, VGG16, ResNet-50, ViT-B/16), our detectors match or outperform five baselines (CTT, SortNet, CRM, ContraNet, A2^2D). For CIFAR-10 with 1-Lipschitz SortNet, our reduction delivers 100%100\% certified detection at the lowest FPR among compared certified detectors; on the standard CIFAR-10 VGG16, our detectors reject all evaluated in-budget adversarial examples, with 62-82% both rejected and formally certified.
Oct 10, 2026

Adversarial Gradient Forcing for Robust Few-Step Autoregressive Video Generation

Autoregressive video generation models generate videos sequentially, with each new block conditioned on previously generated blocks. By training on the model's own rollouts, Self Forcing and its follow-up methods substantially mitigate exposure bias caused by the mismatch between training- and inference-time history distributions. However, these models still suffer from error accumulation during long-horizon generation. We identify a key underlying limitation: the model remains highly sensitive to errors in its generated history, allowing small deviations to be amplified through subsequent generations. We refer to this underexplored problem as the local history robustness gap. To address this gap, we introduce Adversarial Gradient Forcing (AGF), a framework designed to improve the robustness of few-step autoregressive video models to perturbations and accumulated errors in their own generated histories. AGF uses distribution matching gradients from future block predictions to select adversarial perturbations of self-generated histories. It then jointly trains the generator on the original and perturbed histories to improve the robustness of future generation. Extensive experiments show that AGF achieves the highest VBench Total score on 60-second video generation and the best visual quality on four-minute video generation. Notably, AGF achieves such long-horizon robustness while requiring only 5-second rollouts for training.
Oct 9, 2026

Natural Code Transformation Confuses Agents in Vulnerability Analysis

Having demonstrated a strong potential for automating vulnerability discovery, AI agents can also be used to attack software systems at scale. Today's software systems need mechanisms to level the playing field by slowing down potential attacks, giving them time to patch vulnerabilities and strengthen software. Along this line, our study of agent trajectories in vulnerability analysis shows a surprising finding: agents produce dramatically different results across real-world code commits that carry the same functionality and the same vulnerability. This phenomenon appears consistently in multiple code domains and vulnerability categories. It motivates us to study natural and functionality-preserving code transformations derived from real-world software development, and their potential as a defense against attacker agents. We build a corpus of natural transformations by mining recurring development patterns from real-world code commits, and apply them to evaluate impact on agentic vulnerability analysis. Our results show that even a single form of transformation can effectively "confuse" frontier agents, e.g., Claude Mythos 5.2 with Claude Code, reducing successes in vulnerability discovery. We also study different agent failures, whether transformations can be composed to provide stronger protection, and adaptive attackers who seek to reverse them. Overall, our study of natural code transformation significantly expands the research space of using code transformations to defend against malicious agents.
Oct 9, 2026

QCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Human Action Recognition

Skeleton-based human action recognition has gained increasing attention due to the stability of skeleton data across diverse environments and advances in motion capture technologies. Following the success of supervised learning approaches, self-supervised learning approaches, particularly contrastive learning ones, have achieved impressive performance. However, they remain vulnerable to adversarial attacks. In this work, we propose a plug-in robustification module via quantization for contrastive learning in self-supervised skeleton-based human action recognition (QCLR), which enhances the robustness of representations against adversarial attacks while preserving their representational capability. Specifically, we employ a dual-level quantization scheme across the encoding pipeline, which breaks the gradient propagation and absorbs small adversarial perturbations within the quantization bins. To mitigate the impact of inevitable quantization error, we further design an attention-guided multi-faceted quantization strategy to maintain the representation quality. Experiments on several benchmark datasets demonstrate that integrating QCLR into a progressive lineage of mainstream contrastive learning models substantially improves robustness against both gradient-based white-box and gradient-free black-box adversarial attacks, while preserving highly competitive classification accuracy.
Oct 8, 2026

RobustLDS: Learning linear dynamical systems under adversarial corruptions

We consider the problem of learning linear dynamical systems under adversarial contamination from a single trajectory of length TT. While identification of linear dynamical systems itself is well-studied, the problem of robust system identification under adversarial contamination is relatively less explored. In this work, we study the setting where a fraction of the TT observations are contaminated by adversarial outliers. We propose different estimators based on relaxations of least-trimmed squares along with an alternating minimization algorithm. Furthermore, we also propose two estimators which exploit the group-sparsity (through penalization/hard-constraints) of the outliers. For the estimator with group-sparse penalty, we derive non-asymptotic error bounds which establish its robustness to outliers. We also show empirically that the proposed estimators work well in practice.
Oct 8, 2026

Collaboratively Guided Adversarial Robust Distillation with Teacher-Favorable Examples

Adversarial distillation transfers robustness from high-capacity teachers to compact students. Existing adversarial distillation methods mainly use teacher predictions on clean or adversarial examples to supervise student learning. However, teacher-favorable supervision within the perturbation neighborhood remains underexplored in adversarial distillation. We therefore propose Collaboratively Guided Adversarial Robust Distillation (CGARD), which jointly optimizes distinct student-adversarial and teacher-collaborative examples within the same perturbation neighborhood. The teacher-collaborative example is constrained to incur no greater cross-entropy loss under the teacher than the clean input. CGARD combines collaborative teacher guidance with adversarial teacher supervision to improve robust knowledge transfer. Experiments on CIFAR-10 and CIFAR-100, including white-box evaluation and additional black-box transfer evaluation, demonstrate consistent robustness improvements over strong adversarial distillation baselines.
Oct 7, 2026

How Hackable Is Your Speech Quality Metric? A Corrected Protocol, a Benchmark, and What Patching Buys

Speech quality predictors are increasingly used as rewards, yet no agreed measure of their hackability exists. The usual measurement has two flaws. First, the perturbation reaches the predictor through a processing chain -- here a neural codec -- that shifts the score on its own, which scoring against the raw input charges to the attack. Referencing the unperturbed round trip instead changes measured hackability by up to a factor of four (0.31 to 0.08 for one defence). Second, one trained attacker is a sample, not a measurement: five attackers differing only in random seed reach success rates from 0.00 to 0.38 against one fixed predictor, so a defence claim needs the worst case over several. Under this protocol, four published predictors differ widely: NISQA is hacked on 90% of utterances, SSL-MOS on 21%, DNSMOS on 14% and UTMOS on 6%. We then audit a closed attack-detect-patch loop. It hardens the predictor only in its own attack space, by less than the spread between attackers; a random-perturbation baseline matches it; and it costs up to 0.30 system SRCC out of domain. Enhancers post-trained against patched predictors hack them far less (PESQ -0.03 versus -0.23). Code, preregistration and run outputs are released.
Oct 7, 2026

Detection-Guided Adaptive Purification with Diffusion Models for Robust Audio Deepfake Detection

Audio deepfake detectors remain vulnerable to adversarial perturbations that suppress the acoustic cues used for detection, allowing manipulated utterances to evade the detector. Although existing defenses can improve robustness, they require retraining the detector or introduce additional distortion. Diffusion-based purification instead leaves the pretrained detector unchanged, but existing methods use the same purification strength for all inputs, creating a trade-off between removing adversarial perturbations and preserving the subtle spoofing cues needed for detection. In this paper, we propose Detection-Guided Adaptive Purification (DGAP), a diffusion-based defense that adjusts purification strength per input. Building on the observation that a light purification perturbs the detector score of an adversarial input far more than that of a benign one, the framework uses the resulting score shift as a reference-free indicator of adversarial manipulation. Inputs with small shifts are passed unchanged, whereas flagged inputs undergo stronger purification before final detection. We evaluate the framework against three adversarial attack settings across three deepfake detectors, and compare it with nine existing defenses. Our results show that DGAP achieves the best defense performance across all detectors while leaving benign inputs nearly unaffected, and remains effective under the defense-aware adaptive attack.
Oct 7, 2026

MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking

In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certification on such inputs within a patch bound can verify their label benignity and should retain high prediction accuracy. However, existing smoothing-based and masking-based recovery defenders cannot achieve both simultaneously: they degrade the prediction accuracy much and cannot verify the benignity of the returned label of an adversarially patched input, respectively. We propose MRCert, the first masking-based certified recovery defender that shows the feasibility of achieving both. Unlike all existing works to apply a common condition across both types of input (benign and adversarially patched samples) for certification, MRCert infers type-specific necessary properties of deep learning models for both types in post-deployment time and formally relates them to verify the label benignity through a novel type-oriented design of label recovery and certification function pair. Without incurring the degradation in clean accuracy caused by smoothing, experimental results confirm that MRCert achieves 35.1% adversarial certified accuracy on ImageNet at patch size 16 pixels, whereas the SOTA PatchCURE fails completely.
Oct 6, 2026

ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation

Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks often emphasize successful, cooperative interactions and underrepresent adversarial conversation trajectories, thereby limiting the training resources available for developing robust agents. We present ToolRACER, a synthetic data generation pipeline that coordinates user, assistant and tool emulation models to generate and validated multi-turn interactions between a user and an agent. Using ToolRACER, we construct ToolRACERBench a robust multi-turn conversation benchmark spanning six domains, ranging over 55 varied personas, generating a validated corpus of 5.6K conversation trajectories, with approximately 66% of conversations containing failure-prone conversation scenarios. We inject adversarial behaviors, producing validated conversational interaction trajectories that capture realistic, robust scenarios. We evaluate models trained on ToolRACERBench against internal benchmarks, as well as on function calling benchmarks such as τ2τ^2-bench, BFCLv3 and ACEBench to evaluate agentic accuracy and robustness. Models trained on ToolRACERBench improve end to end agentic accuracy across τ2τ^2-bench and ACEBench, demonstrating significant gains when mixed with in-domain dataset in small language models for agent capability tasks.
Oct 6, 2026

VCR-Bench: A Modular Open-Source Benchmark for Video Classification Robustness

Robustness of image classification has several benchmarks, but their video counterparts are absent. In video classification temporal dimension introduces additional degrees of freedom for adversarial attacks, defenses, and preprocessing. Temporal sampling, perturbation budgets, and metric aggregation also interact in ways with no direct analogue in the image setting. Therefore, robustness for video classifiers is studied across scattered, incompatible implementations, making reported numbers hard to reproduce and analyze. We introduce VCR-Bench, a modular open-source benchmark framework that standardizes video loading, wrappers for classifiers, adversarial attacks and defenses, perceptual metrics, configuration presets, and result logging. VCR-Bench currently integrates 30 video classification models, 14 adversarial attacks, and 10 defense wrappers under a common evaluation protocol. We evaluate representative video classifiers, attacks, and defenses on Kinetics-400 subset, reporting clean accuracy, attack success rate, perceptual quality, runtime, and memory usage. VCR-Bench is released with documented installation, reproducible run presets, component-extension interfaces, and scripts for reproducing the reported results at https://github.com/msu-video-group/vcr-bench.
Oct 6, 2026

Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures

Adversarial training is one of the most reliable defenses against adversarial attacks, but its high computational cost must generally be paid anew for each task. Robust foundation models offer a promising alternative: adversarially pretrain a model once and then transfer its robustness to downstream tasks through lightweight adaptation. However, a fundamental question remains open: can robustness acquired during pretraining transfer to unseen tasks without further adversarial training? In this study, we answer this question affirmatively. A single model adversarially pretrained at scale can achieve optimal robustness on new tasks without additional task-specific training. Specifically, we show that, for a family of Gaussian-mixture classification tasks, a sufficiently deep linear transformer adversarially trained across tasks can asymptotically attain the robust Bayes error on previously unseen tasks through in-context learning from clean demonstrations. By contrast, a standardly trained model cannot. We further analyze convergence under gradient flow, an accuracy--robustness trade-off, and demonstration complexity.
Oct 6, 2026

Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff

In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy leakage. State-of-the-art privacy defenses, standard training techniques such as MixUp and Adversarial Training, and undefended models all leak training images at rates 1.16 to 6.59 times higher on FaceScrub under simple adaptive changes to the attack, with the largest increases among defenses reporting the strongest privacy. We further show that measured leakage depends on the feature basis of the external classifier used to evaluate reconstructions: for the same reconstructed images, an adversarially trained Inception evaluator identifies the targeted identity at different rates than the standard Inception evaluator. Our results suggest that standard MIA evaluation can mistake optimization and measurement failures for privacy. These underestimated leakage rates also concealed a broader relationship between privacy and adversarial robustness. Once we adapt the attack and vary the evaluator, reconstruction leakage closely tracks adversarial robustness across recent defenses and standard training regimes, suggesting that robustness provides an attack-agnostic proxy for reconstruction vulnerability that applies far more broadly than previously theorized. This raises an open question: can a practical defense reduce training-data reconstruction without paying a corresponding cost in adversarial robustness?