Adversarial Robustness

Follow this topic Ask about this topic

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

481 papers49 papers in the last four weeks, up 26% on the four weeks before. 0.3% of all new papers.

Aug 13, 2026

QuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing

Typographic attacks pose a critical threat to vision-language models (VLMs) by injecting misleading text into images and causing models to rely on adversarial textual cues rather than visual evidence. Existing defenses often require model-specific modifications, additional training, or access to internal model components, limiting their applicability to modern closed-source VLMs. In this paper, we propose QuISE, a model-agnostic, training-free black-box defense based on query-irrelevant semantic editing. QuISE first identifies text regions likely to affect the current query through influence-aware text localization. QuISE then replaces these regions with two semantically distinct replacement texts that are irrelevant to both the query and the image. The final answer is determined by answer consistency across the edited images. Extensive experiments on three typographic-attack benchmarks, four attack settings, and four VLMs show that QuISE consistently improves defended accuracy. QuISE achieves a recovery rate of 67.9-75.0% with a harm rate of 0.5-1.1%.

Shubin Lu, Jiaqi Yin, Yihao Huang

School of Software, Northwestern Polytechnical University, Xi’an, China · Software Engineering Institute, East China Normal University, Shanghai, China

VLM Robustness Adversarial Attacks on VLMs Adversarial Robustness

Aug 10, 2026

SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks

Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented scenarios. This necessitates the need to evaluate the semantic robustness of perception models; conformance of behavior to high-level requirements over real-world perceptual variability. To address this, we propose SeFaR, a framework for systematic semantic-feature-centric testing of vision models. Given a natural-language requirement and a set of satisfying inputs, SeFaR evaluates robustness with respect to diverse realistic semantic variations that preserve requirement satisfaction. The approach employs a novel hierarchical concept model enabling structured exploration of the feature space and incorporation of domain knowledge via user-defined concepts. State-of-the-art diffusion and vision-language models are leveraged to generate photorealistic semantics-preserving perturbations and identification of previously unknown features impacting behavior. A feedback-driven adaptive process is adopted to generate interpretable failure-inducing semantic concepts along with corresponding test inputs. Evaluation on case studies demonstrates that the proposed framework effectively satisfies requirement preconditions while identifying requirement-independent features that influence model decisions, enabling it to both uncover faults and relate them to such features.

Nusrat Jahan Mozumder, Divya Gopinath, Corina Pasareanu +1

University of Virginia · USA · KBR Inc., NASA Ames +1

Neural Network Verification Neural Network Robustness Adversarial Robustness DNN Testing Automated Test Generation

Aug 10, 2026

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

Advances in advanced artificial intelligence tools have sparked research in robot autonomy, but the development of such systems has largely focused on execution rather than verifying the feasibility actions planning models propose. Like general-purpose LLMs, robotics planning models carry risks: biased toward user-specified goals, they may suggest actions misaligned with scientific ethics, they may be unsafe due to an inability to "remember" prior safety risks, or they may be vulnerable to adversarial attacks on the autonomy ecosystem. We propose a LLM-driven verification layer between planning and execution to evaluate action permissibility. Our LLM-as-a-Judge ensemble combines chain-of-thought reasoning across models and synthesizes those expert judge outputs, mirroring a combination of a mixture of experts and self-consistency approach. This layer serves as middleware, gating plans from the server's planning module before they reach the MCP server and therefore the robot's low-level controls: plans are approved, rejected for reformulation, or escalated for human review. With this system, we achieve near 85% precision across accept/escalate/reject categories 97% containment of adversarial attacks, with negligible errors between accepting and rejecting tasks, and errors mostly manifesting at the escalate boundary.

Rohan Bhagra, Mahantesh Halapannavar, Uddhav Bhattarai

Carnegie Mellon University, Department of Information Systems

Large Language Model-Based Robot Planning Adversarial Robustness Robot Safety LLM Agent Safety

Aug 10, 2026

Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias. Existing methods mitigate this issue by correcting class priors or adapting class wise robust supervision, yet they treat each class in isolation and fail to identify which boundaries drive long tailed collapse. We propose a Confusion Geometry Rebalancing method (CGRm) for long tail adversarial training, a plug in framework that leverages directed robust errors as training signals. CGRm leverages periodic robust evaluations to derive source class loss weights, class wise robust coefficients, and a directed confusion geometry graph. The method then couples feedback weighted robust optimization with graph guided margin correction, thereby boosting the robustness of vulnerable classes and sharpening the critical boundaries that drive long tailed performance degradation. Experiments on long tailed benchmarks show that CGRm achieves consistent robust performance gains over existing methods, with ablations validating the contribution of each component. We provide the code in the supplement.

Mengnan Zhao, Geyong Min, Lihe Zhang +2

School of Computer Science, Anhui University, China · Department of Computer Science, University of Exeter, UK · School of Information and Communication Engineering, Dalian University of Technology, China +1

Adversarial Training Long-Tailed Classification Adversarial Robustness Adaptive Loss Weighting

Aug 9, 2026

Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles

Traffic sign recognition (TSR) models based on deep neural networks achieve strong clean-data performance but remain vulnerable to physically realizable adversarial attacks, including shadow perturbations, natural-light interference, and printed patches. Existing defenses often improve robustness against one attack type while degrading performance on others, and can reduce clean accuracy. We propose LAMDA (Language-Anchored Model for Direction Alignment), a training framework that transfers language-grounded structure into TSR models without using adversarial examples or adding inference-time overhead. LAMDA builds two fixed prototype banks from VLM-generated sign descriptions and class names using a frozen OpenCLIP text encoder, and uses them to supervise visual features through two complementary auxiliary losses during training. At inference, the adapter and prototype banks are discarded, leaving a standard backbone and classifier. Evaluated on GTSRB and LISA across four backbones and three physical attack types, LAMDA is the only method among ten evaluated that consistently improves robustness across all attack-backbone-dataset combinations, with gains of up to +12.5 pp under shadow attacks and +13.2 pp under natural-light attacks, while preserving or improving clean accuracy in nearly all cases.

Pedram MohajerAnsari, Amir Salarpour, Mert D. Pesé

Clemson University, Clemson, SC, USA

Adversarial Robustness VLM Distillation Autonomous Driving Perception Physical Adversarial Attacks

Aug 7, 2026

TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning

Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead. However, its split architecture introduces unique attack surfaces, rendering it vulnerable to diverse poisoning attacks. Most existing defenses fail to exploit the split paradigm, limiting their ability to detect and contain malicious behaviors at an early stage. To bridge this gap, we propose Target-Oriented Feature Decoupling (TOFD), a unified framework that jointly enables proactive detection and robust optimization against a wide range of poisoning attacks. TOFD operates in three stages: (1) Target Inference, which identifies potential attack targets by refining class-wise safe zones via class-specific Margin Perturbation (MP); (2) Sample Purification, which adaptively filters poisoned smashed data using thresholds calibrated through cross-class min-max normalization of MP; and (3) Decoupling Optimization, which leverages an adversarial guidance model to capture attack-induced patterns and decouple their influence during optimization, thereby suppressing residual adversarial effects. We provide theoretical guarantees for the convergence of TOFD. Extensive experiments on five datasets demonstrate that TOFD consistently outperforms state-of-the-art defenses under diverse attack scenarios, achieving superior robustness with low computational overhead suitable for practical deployment.

Yuhan Xie, Jingrong Huang, Chen Lyu

Shanghai University of Finance and Economics MoE Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai, China

Adversarial Robustness Split Federated Learning Data Poisoning Attacks Federated Learning

Aug 7, 2026

Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers

Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical systems. Detection transformers have emerged as leading object detectors, yet their adversarial robustness remains comparatively underexplored. Most existing attacks target the detection output rather than the attention mechanism that makes these models distinctive. In this paper, we introduce the first attack that directly optimizes an encoder-attention objective under an imperceptible, bounded

\ell_\infty

perturbation. Rather than introducing an attacker-owned sink token through a visible patch, it drives the model's own attention toward a corrupted target. We argue that encoder attention concentrates the model's spatial reasoning, so corrupting it propagates through the detection pipeline more disruptively than perturbing the detection output alone. Our attack reduces DETR-R50 mAP on COCO from 42.1 to 0.97, a

\sim 4\times

reduction in resulting mAP over the strongest existing attack under an identical perturbation budget and iteration count. We further show that this vulnerability is not specific to a particular corruption objective: across four qualitatively distinct targets, dispersion, re-ranking, permutation, and peak-suppression, detection consistently drops below 3 mAP, suggesting that the weakness arises from disrupting the attention structure itself rather than from any single target. Finally, we demonstrate that the attack generalizes across attention formulations, reducing DINO-Swin-L from 56.8 to 1.44 mAP against 7.3 for the strongest prior attack, establishing state-of-the-art on both dense and deformable attention.

Ridma Jayasundara, Shaheer Mohamed, Tharindu Fernando +6

Signal Processing, Artificial Intelligence and Vision Technologies Group (SAIVT), Queensland University of Technology · Institute of High-Performance Computing, Agency for Science, Technology and Research, Singapore · School of Computing, National University of Singapore +1

Adversarial Attacks Adversarial Robustness Detection Transformer Attention-Based Adversarial Attacks Adversarial Attacks on Object Detectors

Aug 6, 2026

Universal Concept Disruption for SAM3 Image Segmentation

SAM3 extends promptable segmentation from geometry-driven mask prediction to open-vocabulary concept segmentation, where a text-conditioned grounding model decides whether a concept is present and segments all matching instances. While this presence-gated design improves concept-level prediction, its adversarial robustness remains unexplored. In this paper, we introduce Universal Concept Disruption (UCD), the first universal cross-concept adversarial attack tailored to SAM3 image segmentation. UCD learns a single bounded image perturbation from (image, noun-phrase) pairs and attacks SAM3 as an integrated concept-grounding system. It jointly disrupts the text-conditioned input path, maximizes divergence in prompt-shared visual features, suppresses the final presence-gated concept scores, and corrupts the spatial validity of retained masks through area collapse and clean-mask Dice disruption. Across SACo-Gold, LVIS, RefCOCO, PhraseCut, and OpenImages datasets, UCD consistently outperforms all baselines under a matched evaluation protocol, reducing average mask AP from 59.43 to 18.73 and average cgF1 from 50.32 to 20.49. The learned perturbation also transfers to SAM3.1 and to SAM3 video inference without re-optimization, while prompt ensembling, lightweight head fine-tuning, and temporal filtering provide limited recovery.

Hao Wang, Yuxuan Zhang, Wei Yang

School of Computer Science and Technology, University of Science and Technology of China, Hefei, China · School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China · Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China +1

Promptable Image Segmentation Adversarial Robustness Adversarial Perturbations Open-Vocabulary Semantic Segmentation

Aug 6, 2026

CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal

Many single-cell annotation tools refine an initial cell label using nearby cells or cluster-level voting. We study whether this refinement can be manipulated without changing the target cell. We introduce CohortHijack, a robustness audit that removes selected non-target cells from the query cohort while preserving the target expression profile, base prediction, and trained model. We evaluate random and structured removal methods, together with greedy, multi-start, and beam search, on PBMC3K and Paul15 using logistic regression and calibrated linear SVM classifiers. Structured removal was consistently stronger than random removal on Paul15. Multi-start search changed 24.33% of linear-SVM targets and 19.67% of logistic-regression targets while removing a small fraction of the cohort and keeping mean collateral changes below 0.4%. Ablations confirmed that the effect disappeared when neighborhood refinement was disabled. We also evaluated CellTypist majority voting, where independent predictions remained unchanged across all evaluations, but refined labels changed after small companion-cell removals. These findings identify query cohort composition as a target-preserving attack surface in single-cell annotation.

Arash Vashagh, Yasmin Vashagh

Faculty of Computer Science, University of New Brunswick, Fredericton, New Brunswick E3B 5A3, Canada · Farzanegan Amin 2 High School, Isfahan, Iran

Adversarial Robustness Single-Cell Transcriptomics

Aug 5, 2026

MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs

To adopt the Vision Transformers (ViTs) in resource-constrained environment, token pruning is widely used to reduce computational cost without impacting accuracy. However, adversaries have developed targeted attacks against said token pruning techniques to undermine such attempts to make ViTs efficient. In this paper, we propose MOAT, a model-agnostic pre-processing defense pipeline that applies a combination of input transformations to protect efficient ViT implementations against adversarial efficiency attacks. MOAT operates directly on the input without requiring modifications to the model architecture or token pruning mechanism. Experimental results demonstrate that, across all evaluated ViT models, MOAT limits GFLOPs degradation under adversarial attacks to within 3.4% of the original unattacked model.

Anadi Goyal, Nandish Chattopadhyay, Chandan Karfa +2

Indian Institute of Technology Guwahati, India · Nanyang Technological University, Singapore · Prince of Songkla University, Phuket Campus

Adversarial Attacks Vision Transformer Adversarial Robustness

Aug 5, 2026

Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle

Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technical interventions must be applied earlier, when content is released or accessed. This survey examines the protective paradigm that has grown around this intervention point, which we call adversarial attacks for good. Perturbations and structured signals long studied as attacks on learned models are instead applied by data owners, creators, platforms, or auditors to disrupt unauthorized automation or support later accountability. Five research communities have arrived at this inversion largely independently, each addressing a different stage of a visual asset's lifecycle: privacy filters against unwanted recognition at sharing time, unlearnable examples against unauthorized training, generative safeguards against malicious editing or imitation, adversarial CAPTCHAs for access control against automated agents, and provenance mechanisms for post-circulation attribution. Although developed in separate venues with incompatible success criteria, many of these methods exploit persistent gaps between human perception, semantic interpretation, and machine inference, suggesting that the paradigm remains relevant as visual pipelines evolve toward multimodal models and autonomous agents. To make their claims comparable, we evaluate all five families along shared axes of transferability, adaptability, and deployment readiness. Across the lifecycle, we find that most protections are still validated mainly against static or weakly adaptive adversaries, while evidence beyond controlled benchmarks remains scarce. We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.

Jiaming Zhang, Boyang Chen, Zherui Li +14

College of Computing and Data Science, Nanyang Technological University, Singapore · School of Computing and Information Systems, University of Melbourne, Australia · School of Computing and Information Systems, Singapore Management University, Singapore +3

Data Provenance Adversarial Robustness Unlearnable Examples

Aug 4, 2026

Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models

Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not recover it: combiners such as majority voting trade recall for precision and are brittle to coordinated failures. Prior metacognitive methods learn logical rules that flag a model's errors, but rely on hand-authored domain-knowledge cues (object-size priors, segmentation masks) that do not transfer to genuinely novel scenes. We show that this metacognitive layer can be learned without any domain knowledge by exploiting vector-space geometry: per-model Label Vector Pools (LVP), built from each model's own training embeddings, yield error-detection rules from the geometry of detections relative to training-determined prototypes, reaching parity with domain-knowledge rules to within

0.002

every F1 on test set. Because the approach remains neurosymbolic, these geometric rules share a single logical framework and can still be complemented by domain knowledge when available. We frame the fusion of multiple imperfect ViT-based detectors as a consistency-based abduction problem solved at test time by an exact Integer Program (IP) and a polynomial-time heuristic. On an aerial-imagery benchmark of 15 weather-shifted test sets and six ViT detectors, our domain-knowledge-free layer matches the strongest majority-vote variant on clean data (within

0.005

F1) and, unlike every majority-vote baseline, retains its performance under a coordinated label-flipping attack: at a

90\%

flip rate it averages

0.42

F1 versus

0.35

for MV-Plurality (a

22\%

relative gain) and attains the highest F1 on every test set once the flip rate exceeds

0.4

Mario Leiva, Yue Ma, Qinru Qiu +2

1DCIC, Universidad Nacional del Sur (UNS) & ICIC (UNS-CONICET), Bahía Blanca, Argentina · 2Syracuse University, Syracuse, NY USA

Distribution Shift Abductive Reasoning Ensemble Learning Adversarial Robustness Object Detection

Aug 4, 2026

Understanding Fault Tolerance of Adversarially Robust Pruned Models

Deep neural networks (DNNs) deployed on resource-constrained neuromorphic hardware face three concurrent challenges: the need for model compression through pruning, vulnerability to adversarial input perturbations, and susceptibility to hardware-induced weight faults such as stuck-at-zero errors. While each of these factors has been studied in isolation, their combined effects on model reliability have received little attention. This paper presents an empirical investigation of how pruning, adversarial training, and hardware fault injection interact to affect the robustness of convolutional neural networks. Using a compact three-layer CNN trained on MNIST, we conduct three experiments: (1) comparing the fault tolerance of naturally and adversarially trained models under simultaneous hardware faults and adversarial attacks, (2) evaluating how pruning affects adversarial robustness, and (3) characterizing the joint accuracy surface across fault rates, adversarial perturbation magnitudes, and pruning levels. Our results show that adversarial training improves robustness against input perturbations but increases sensitivity to stuck-at-zero weight faults. Contrary to intuition, pruning did not significantly increase fault sensitivity, and varying the pruning level had little effect across fault rates and attack strengths. These results highlight the need to jointly consider adversarial robustness and hardware reliability.

Manali Dangarikar, Cory Merkel

Brain Lab Rochester Institute of Technology Rochester, NY, USA

Adversarial Training Neural Network Robustness Adversarial Robustness Neural Network Pruning

Aug 4, 2026

Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining

Near-duplicate image matching is crucial for trust and safety, provenance verification, copyright enforcement, and large-scale visual search. Modern platforms increasingly rely on deep perceptual hashes, which map visually similar images to nearby representations despite common image transformations. However, adversarial perturbations can cause near-duplicates to evade matching. We present DualShield, a plug-in defense that improves the robustness of existing deep perceptual hashes without retraining or modifying their underlying models. DualShield combines matching-time randomized smoothing, which aggregates decisions over perturbed reference-query pairs, with publication-time hardening, which adds an optimized imperceptible perturbation to each reference image before publication. Together, these mechanisms provide certified and empirical robustness. DualShield achieves a certified

\ell_2

radius of approximately 0.3, guaranteeing that query perturbations within this radius cannot evade matching. We further evaluate it against adaptive white-box, black-box, and image-transformation attacks. Across eight deep perceptual hashes and three datasets, DualShield substantially reduces attack success rates while preserving low collision rates. These results show that deep perceptual hashes can be strengthened without costly retraining by improving the matching procedure and hardening reference images before publication.

Bangjie Sun, Nayoung Kim, Mun Choon Chan +1

National University of Singapore (NUS) · Korea Advanced Institute of Science and Technology (KAIST)

Image Matching Adversarial Robustness Certified Robustness

Aug 3, 2026

Does the Competitive Component of Adversarial Self-Play Improve Legal Reasoning? A Controlled Negative Result

Adversarial self-play is an appealing recipe for legal reasoning: have a student model draft an argument, have an adversary attack it, and reward the student when its argument survives the attack. We designed exactly such a training signal -- a verifiable "survival" reward in which both the student's cited authorities and the adversary's counter-authorities are checked by a citation verifier, so that survival is decided on verified grounds rather than rhetoric, and fabricated citations are automatically neutralized. We then asked a narrow but important question: does the competitive component itself -- the adversary and the survival reward -- add anything on top of an otherwise identical non-competitive training run? Across four independent tests -- a bootstrap comparison, a two-seed replication, a paired per-case adversarial-robustness comparison, and a blinded head-to-head judgment of generated arguments, plus a follow-up pilot with a deliberately strengthened self-play adversary -- the competitive component produced no reliable benefit. The blinded judgment gave a 49% win rate (binomial p approx. 1.000); the strengthened-adversary pilot gave a 50% win rate (32:32, p approx. 1.000). An early apparent +29% advantage reversed and proved to be a small-sample artifact. We report this as an honest negative result. The value of the paper is reproducibility and the sharing of concrete pitfalls: an initially promising metric that inverted on more data, and an adversarial-robustness metric that silently collapsed to plain recall once the adversary stopped citing the same authorities as the gold answer. This null is consistent with, and reconfirms in the legal domain, the conclusion of the companion coding-domain study (Kim, 2026, arXiv:2607.08255) that the value of multi-teacher curricula arises from constructing a verifiable environment rather than from competition itself.

Miseog Shawn Kim

Preprint, 2026-08-02

Adversarial Robustness Reinforcement Learning with Verifiable Rewards Legal Reasoning

Aug 2, 2026

No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks

With the rapid release of open-weight large foundation models, safety threats are shifting from black-box jailbreaks to neuron-level white-box attacks that directly identify and manipulate safety-related neurons. Existing alignment methods often investigate the safety behavior on a small number of neurons, creating fragile single point of failure with limited redundancy. To address this issue, we propose distributed safety alignment (DSA), which redundantly encodes safety capabilities across multiple computational neurons, ensuring that the model maintains its safety baseline even when critical safety neurons are disrupted. Specifically, we localize the intervention to the inputs of the down-projection layers in language-side feed-forward networks and treat each feature coordinate as the activation of an individual neuron. DSA then combines neuron activations with loss gradients to compute a direction-aware first-order Taylor score that globally identifies the neurons that contribute most to the current refusal behavior of the model. Finally, targeted disruption via deterministic masking and stochastic dropout is coupled, forcing the model to abandon narrow safety neurons and redundantly encode safety behavior across multiple compensatory neurons. Extensive experiments show that DSA substantially improves robustness against white-box neuron-level safety attacks while preserving the model's general language and multimodal utility.

Simiao Xie, Chuancheng Shi, Shangze Li +5

The University of Sydney · NExT++ Research Centre, National University of Singapore

LLM Alignment Adversarial Attacks on LLMs Adversarial Robustness LLM Safety Alignment

Jul 30, 2026

ZAPs: A Reward Attribution Framework for DeFi Ecosystems with Adversarial-Robust Scoring via Parallel Anomaly Ensemble Detection

Incentive programs are central to user acquisition in decentralized finance, but many reward systems rely on raw volume, transaction count, and wallet count, making them vulnerable to bots and sybil operations. We present ZAPs, a reward attribution framework that combines economic contribution scoring with adversarial robustness. A composite activity score uses protocol-specific percentile normalization to limit whale dominance while preserving differentiation among users. A two-layer weighting mechanism combines protocol share within sector and sector share within the ecosystem, which reduces the profitability of farming small protocols. We show that the maximum reward obtainable from any protocol is bounded by that protocol's global volume share. ZAPs also introduces a four-layer defense stack consisting of transaction-level integrity checks, a parallel anomaly ensemble, post-distribution behavioral memory, and graph-based sybil clustering. The anomaly ensemble combines a one-class reconstruction model with an isolation forest and applies graduated rather than binary penalties. On 1,073 labeled malicious wallets covering 124,638 transactions, the ensemble achieves 0.923 +/- 0.013 ROC-AUC, compared with 0.891 +/- 0.016 for the reconstruction model alone, when the isolation forest is trained on benign wallets. Training it on the pooled population reverses its polarity and removes the ensemble gain. Controlled simulations reduce adversarial reward capture by 30-90 percent while legitimate-user scenarios change by 1-8 percent. Live campaigns recorded a 56 percent reduction in sybil allocation, a 49 percent increase in quality-wallet participation, and a 50 percent reduction in sell pressure.

Girish G N, Ashutosh Sahoo, Ajay Bhat +4

Zeru Finance · The Ohio State University, USA

Adversarial Robustness Financial Fraud Detection Decentralized Finance Unsupervised Anomaly Detection

Jul 30, 2026

Improving the Robustness/Accuracy Tradeoff Against Adversarial Attacks Using Information Bottleneck Distillation Through Dual Teachers

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.

Vincent Ryusuke Takahashi, Yoshinari Takeishi, Jun'ichi Takeuchi +1

Joint Graduate School of Mathematics for Innovation Kyushu University · Faculty of Information Science and Electrical Engineering Kyushu University · Université Savoie Mont Blanc

Adversarial Training Neural Network Robustness Adversarial Robustness Multi-Teacher Knowledge Distillation Knowledge Distillation Image Classification+1

Jul 30, 2026

Revisiting the Adversarial Robustness of Graph-Based Traffic Forecasting

Traffic forecasting by graph-based AI is a critical component of intelligent transportation systems, motivating security research on robustness to malicious sensor readings. We argue that prior robustness evaluations are largely shaped by unrealistic threat models and untargeted objectives, so both attacks and defenses must be revisited. We study a practical adversary with limited model knowledge and the ability to monitor and manipulate only a few road sensors. More importantly, practical attacks can be localized to specific links or routes, causing incorrect estimated arrival times or unnecessary rerouting while leaving the broader network largely unaffected. This targeted setting remains underexplored, and defenses such as adversarial training do not transfer well from the norm-bounded attacks they train on to structurally different, physics-aware attacks that mimic genuine congestion. We therefore reframe robustness as a detection problem, introducing a learned physics-informed detector whose output is fed to a hardened forecaster as an input feature and trained against adaptive attacks with the forecaster fixed. We evaluate across a variety of model architectures and benchmarks. The physics-aware attack multiplies target-link error several-fold while the network-wide error barely moves, and adversarial training, tuned to norm-bounded perturbations, barely dents it. Our detection--mitigation defense improves even on adversarial training hardened against the physics-aware attack itself, on

13

of

15

model--dataset settings and by the widest margin on a held-out attack, at near-zero clean cost. The results emphasize the need to examine abstracted AI adversarial attacks under application-specific constraints to assess their true security impacts.

Qingzhao Zhang

The University of Arizoan

Adversarial Attacks Adversarial Robustness Adversarial Example Detection Spatiotemporal GNNs Physical Adversarial Attacks

Jul 27, 2026

EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability

Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their brittleness against content-injection attacks; and (iv) neglect the computational requirements for deployment, risking slow inference on endpoints. For these reasons, we develop EXE-Bench, a comprehensive benchmark of AI-based Windows malware detectors. EXE-Bench assesses performance, temporal and adversarial robustness, and computational overhead, aggregating them into a single score for direct and fair model comparison. Through EXE-Bench, we highlight how evaluations conducted only after deployment are suboptimal and unable to provide a complete picture of their performance. In particular, through our analysis, we remark how much domain knowledge instilled through feature engineering is still extremely useful in this domain, resisting both time and adversarial attacks, in stark contrast with most of the deep networks that only excel right after deployment.

Andrea Ponte, Daniel Gibert, Matous Kozak +5

Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genova, Italy · Artificial Intelligence Research Institute (IIIA-CSIC), Spain · Department of Information Security at Faculty of Information Technology, CTU in Prague, Czech Republic +2

Efficient Inference Adversarial Robustness Malware Detection

Jul 24, 2026

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety

A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech. Preventing such harmful fine-tuning while retaining benign adaptability remains difficult: the only prior method with an explicit curvature certificate, spectral deformation, inflates curvature globally and thereby obstructs benign adaptation along with harmful adaptation. We propose HarmAlign, which applies function-preserving spectral deformation along a estimated contrastive activation subspace. We derive finite-sample bounds for the estimated subspace energy and the resulting local harmful-distribution curvature lower bound. A stability--progress dichotomy for constant-step gradient descent turns the certified curvature into conditional convergence-rate control. Empirically, within a fixed-architecture, finite-budget first-order threat model, HarmAlign blocks direct fine-tuning and three data- or objective-adaptive attacks across a hazardous-knowledge relearning setting and a harmful-assistance fine-tuning setting, while the protected benign tasks remain trainable. The block persists across the tested first-order optimizer variants over every attack checkpoint, and under out-of-distribution harmful fine-tuning, and it extends to important cases in our threat model: accidental safety degradation and emergent misalignment.

Domenic Rosati, Ali Dadsetan, Hong Huang +5

1Dalhousie University · 2Vector Institute for Artificial Intelligence · 3Indian Institute of Management Bangalore

Adversarial Robustness LLM Safety Alignment Adversarial Robustness of Language Models

Jul 23, 2026

Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attacks

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

Yuanhao Huang, Yilong Ren, Jinlei Wang +3

School of Transportation Science and Engineering, Beihang University, 100191, Beijing, P.R China · Zhongguancun Laboratory, 100191, Beijing, P.R China · School of Systems Science and Engineering, Sun Yat-Sen University, 510006, Guangzhou, P.R China +2

Adversarial Training Adversarial Robustness Object Detection Shortcut Learning Physical Adversarial Attacks Adversarial Attacks on Object Detectors

Jul 22, 2026

Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation

Adversarial robustness is commonly evaluated with predefined attack ensembles, such as AutoAttack, at a single perturbation budget

\varepsilon

and on a selective choice of perturbation norms. We argue this formulation is fundamentally limited. First, robustness--perturbation curves may intersect or decay at different rates across models, making single-

\varepsilon

rankings unstable. Second, current ensembles provide no evidence of optimality, leaving an unknown gap to worst-case performance. Third, fixed attack configurations provide no systematic control over the trade-off between attack strength and evaluation cost. To address these limitations, we introduce a unified evaluation framework based on a comprehensive pool of minimum-norm attacks and robustness--perturbation curves across

\ell_0

,

\ell_1

,

\ell_2

and

\ell_\infty

norms. We define the attack frontier as the worst-case robustness estimate the attack pool produces against a model. We then formalize evaluation as a frontier-approximation problem, constructing minimum-norm attack ensembles, optimized subsets of the comprehensive pool, that approach the frontier under a controllable query budget, with larger budgets monotonically tightening the estimate. Furthermore, we define the defense frontier as the maximum robustness across the model set at each perturbation size. We finally propose the Defense Optimality Index to rank defenses by their gap to the defense frontier, providing a ranking without selecting a reference

\varepsilon

. On CIFAR-10 and ImageNet, our ensembles match or exceed AutoAttack on most defenses at every budget tier, at fixed and controllable query cost, offering practitioners a query-controlled, curve-based alternative to fixed-

\varepsilon

evaluation.

Luca Scionis, Luca Melis, Maura Pintor +5

Sapienza University of Rome, Italy · University of Cagliari, Italy · University of Genoa, Italy

Adversarial Attacks Neural Network Robustness Adversarial Robustness

Jul 22, 2026

A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection

Almost all adversarial attacks add an imperceptible perturbation to fool a model. We instead study the opposite: a large, clearly visible perturbation that causes the model to keep its original, correct prediction, even though a human would no longer recognize the image. Prior work showed such examples can be generated at scale but left three questions untested: whether humans really perform worse than the model, whether standard out-of-distribution (OOD) detection and calibration tools catch it, and whether existing defenses mitigate it. We answer all three on MNIST, CIFAR-10, and ImageNet. (i) An independent recognizer proxy drops to ~49% on CIFAR-10 while the model stays at 100% -- a gap a small human pilot (N=5) corroborates directly and that is not explained by signal loss (a matched-magnitude Gaussian control degrades recognizability faster); a CLIP zero-shot proxy confirms the gap at ImageNet scale too. (ii) Confidence- and energy-based OOD detectors and calibration are structurally blind (0% detection, ECE ~= 0), while a feature-space Mahalanobis detector flags 100% -- but is evaded by an adaptive attacker at no cost to success. (iii) No classical defense, including adversarial training (45% robust accuracy), reduces attack success (correlation with large-epsilon_l resistance r ~= 0). A mechanistic analysis further shows the attack destroys low-level texture far faster than edge/shape structure.

Ali Borji

BrainChip Inc., Laguna Hills, CA, USA

Adversarial Robustness Adversarial Examples OOD Detection

Jul 21, 2026

1-Lipschitz Neural Networks on Hadamard Manifolds

Controlling the Lipschitz constant of a neural network is a standard way to promote robustness and stability. Most existing constraining strategies are designed for Euclidean spaces. In this work, we construct and analyze a class of 1-Lipschitz neural networks on Hadamard manifolds. Our layers are of gradient-descent type,

1

-Lipschitz, and quasi-

α

-firmly nonexpansive. The core building blocks of the proposed architecture are Busemann functions, and we exploit the properties of Busemann gradient flows to design

1

-Lipschitz geometry-preserving layers. We provide explicit constructions and examples for hyperbolic manifolds and the manifold of symmetric positive definite (SPD) matrices. We test the proposed architecture in two numerical experiments: robust classification on the Poincaré disk and masked-Wishart covariance reconstruction. On the Poincaré disk, the proposed networks yield robust classifiers under hyperbolic perturbations. On the SPD manifold, we train SPD-valued denoisers and adopt them as a Plug-and-Play prior for a masked-Wishart covariance reconstruction problem. We show improved results from the nonexpansive denoiser over static, data-only, and Log-Euclidean denoising baselines, and empirically test its convergence properties.

Davide Murari, Marta Ghirardelli, Ben Adcock +3

Department of Applied Mathematics and Theoretical Physics, University of Cambridge · Department of Mathematical Sciences, Norwegian University of Science and Technology (NTNU) · Department of Mathematics, Simon Fraser University

Riemannian Neural Networks Neural Network Robustness Adversarial Robustness Lipschitz Neural Networks

Jul 20, 2026

Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT

Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most reported detection accuracies, however, are measured on clean, in-distribution test data rather than on emails deliberately altered to evade detection. This paper reports a controlled, pairwise comparison of two phishing-detection approaches a TF-IDF + Logistic Regression baseline and a fine-tuned DistilBERT transformer trained on a unified corpus of 82,255 emails drawn from six public datasets and evaluated under three conditions: normal in-distribution, synthetic phishing, and adversarial phishing. Both models exceeded 98% accuracy on clean data yet degraded sharply under adversarial testing: TF-IDF + LR fell to 64.00% (a 34.59-percentage-point drop) and DistilBERT fell to 63.64% (a 35.40-percentage-point drop) a gap of only 0.36 percentage points, equivalent to a single email in the 275-sample adversarial test set. LIME, SHAP, and attention-rollout analysis indicate the two models relied on different evidence yet showed similar vulnerability. Pairwise error analysis shows the models agreed on 54.9% of adversarial samples but each made a similar number of exclusive errors (24 and 25 respectively), indicating partly complementary rather than identical failure modes. The results show that clean-data accuracy does not predict adversarial robustness, and that adversarial testing should be a standard part of phishing-detection evaluation.

Tanveer Ahmed, Seyedali Pourmoafil

School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield, Herts AL10 9AB, United Kingdom

Adversarial Robustness Cybersecurity Phishing Detection Adversarial Text Attacks

Jul 19, 2026

A Multi-Model Hybrid Defense Approach Against White-box Adversarial Attacks in Computer Network Traffic

It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System (NIDS). However, NIDS faces a major security concern due to its susceptibility to adversarial attacks. Adversarial attacks aim to deceive NIDS by crafting and injecting adversarial examples into the system. These adversarial inputs can deceive the NIDS into misclassifying benign network traffic as malicious. We developed a resilient hybrid defense mechanism aimed to mitigate the impact of two potent adversarial attacks: Fast Gradient Sign Method (FGSM) and Carlini & Wagner (C&W) attack. Our hybrid defense approach leverages the combined strength of two heuristic defense methods: Adversarial Training (AT) and Gaussian Data Augmentation (GDA). GDA provides multi-directional defense, while AT enhances NIDS robustness against specific adversarial vectors. Under pre-attack scenarios, NIDS demonstrated good accuracy and f1-score. However, in the post-attack scenario, its accuracy significantly dropped under FGSM and C&W attacks (0.2649 and 0.4961, respectively). Our proposed hybrid defense method effectively mitigated these adversarial threats, with post-defense accuracy of 96.57% and 89.20% for FGSM and C&W attacks. We evaluated the defense strategy across a range of epsilon and confidence noise factor values (ranging from 0.0001 to 0.0009). This research provides a good direction for future researchers in the emerging area of adversarial machine learning from a security perspective.

Khushnaseeb Roshan

Department of Computer Science, Aligarh Muslim University (AMU), Aligarh, INDIA

Network Intrusion Detection Adversarial Robustness

Jul 17, 2026

Boundary-Seeking GAN-Augmented TabTransformer for Adversarially Robust Intrusion Detection

Machine learning-based intrusion detection systems (IDSs) often suffer from class imbalance and vulnerability to adversarial attacks, leading to degraded detection performance and reduced robustness. This study proposes a TabTransformer framework augmented by the Boundary-Seeking Generative Adversarial Network (BGAN) for flow-based intrusion detection using the CICIDS2017 dataset. BGAN serves a dual purpose by generating synthetic minority-class samples to mitigate data imbalance and producing adversarial samples to evaluate model robustness. Experimental results demonstrate that BGAN augmentation improves TabTransformer's Macro-F1 score from 82.96% to 86.50%, with the largest class-wise improvement observed for Web_Attack (F1 score: 0.29 to 0.61). Robustness evaluation shows that all non-augmented models experienced a 100% Performance Drop Rate (PDR) under adversarial testing, whereas all BGAN-augmented models achieved negative PDR values, indicating improved resilience. Furthermore, the augmented TabTransformer maintained stable and low False Triggered Rate (FTR) values (1.51%-2.92%) across all noise levels, compared with the BGAN-augmented Decision Tree, which reached 49.09% under benign perturbations. These findings demonstrate that BGAN consistently enhances both class balance and adversarial robustness, while the proposed BGAN-TabTransformer framework provides an effective and adaptive intrusion detection solution for adversarial network environments.

Raihan Sultan Pasha Basuki, Aliyah Kurniasih

Department of Computer Science, Universitas Ary Ginanjar, Menara 165, Cilandak No.kav 1 Lt 2 & 18, Jakarta Selatan, 12560, DKI Jakarta, Indonesia

Synthetic Data Augmentation Transformer Adversarial Attacks Network Intrusion Detection Adversarial Robustness

Jul 16, 2026

Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks

Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable deployment of these models. In recent years, some powerful adversarial example attacks have been proposed for the fast and query-efficient generation of adversarial examples, even in black-box scenarios, highlighting the need for scalable, low-cost, and powerful defenses. In this work, we present two contributions to the domain of black-box adversarial example attacks and defenses. First, we propose Random Logit Scaling (RLS), a randomization-based defense against black-box score-based adversarial example attacks. RLS is a plug-and-play, post-processing defense that can be implemented on top of any existing ML model with minimal effort. The idea behind RLS is to confuse an attacker by outputting falsified scores resulting from randomly scaled logits while maintaining the model accuracy. We show that RLS significantly reduces the success rate of state-of-the-art black-box score-based attacks while preserving the accuracy and minimizing confidence score distortion compared to state-of-the-art randomization-based defenses. Second, we introduce a novel adaptive attack against AAA, a SOTA non-randomized black-box defense against black-box score-based attacks that also modifies output logits to confuse attackers, demonstrating its vulnerability against adaptive attacks.

Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh

Department of Computer Engineering Sharif University of Technology

Adversarial Robustness Black-Box Adversarial Attacks Consistent Adversarial Attacks

Jul 15, 2026

Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection

Large language model (LLM)-based intrusion detection systems (IDS) are increasingly studied for security monitoring, yet their robustness against feasible traffic manipulation remains largely empirical. We present Traffic-Aware Randomized Smoothing (TA-RS), a classifier-agnostic certified defense that injects Gaussian noise exclusively into the directly controllable (DC) subspace -- features a remote attacker can modify -- during both fine-tuning and certification, aligning the smoothing distribution with the attacker-controllable subspace. We identify a critical prerequisite: applying standard randomized smoothing to clean-trained LLM-IDS yields weak certified accuracy in three of four (model, dataset) pairs tested (14-33%, at or below random) and only 57% in the fourth (43 pp below the noise-augmented result); noise-augmented fine-tuning recovers to 68-100% on two of three benchmark datasets (at sigma=0.25). At the L_inf-equivalent threshold R_inf = epsilon*sqrt(|DC|) (epsilon=0.05), TA-RS achieves 55-100% certified accuracy on CIC-IDS-2018 and HIKARI-2021, with median certified radii (R approx 0.45-0.96) exceeding R_inf by 1.8-5x (across sigma=0.25-1.00). Against a fairly trained iso-trained RS baseline the residual advantage is dataset-dependent (4-19 pp on CIC-IDS-2018). The larger gap -- up to 72 pp against an isotropic RS baseline that shares the DC-noise-augmented training recipe -- primarily reflects the training-certification mismatch rather than DC alignment alone: isotropic test-time noise perturbs uncontrollable features the attacker cannot exploit, triggering abstention rates up to 68%. RT-IoT2022 probes the limits of the method: it fails under the default fine-tuning recipe but recovers to 76%/69% certified accuracy (LLaMA3-8B/Qwen3-8B) when noise augmentation is increased.

Zhenpeng Li

Randomized Smoothing Network Intrusion Detection Adversarial Robustness LLMs for Cybersecurity Certified Robustness