Adversarial Attacks

Follow this topic Ask about this topic

Adversarial attacks study how deliberately chosen inputs, training data, model parameters, or system interactions can make AI systems fail or behave as intended by an attacker. Common approaches include gradient-based perturbations, black-box query and evolutionary search, generative or semantic changes, physical patches and sensor interference, and poisoning or backdoors. Work spans image, language, audio, graph, and time-series models as well as federated learning, recommenders, robotics, and AI agents, with evaluations on benchmarks and increasingly realistic deployment settings. A central tension is that attacks must be effective and stealthy under practical constraints, while defenses and benchmarks must keep pace with adaptive threats and distinguish digital robustness from real-world resilience.

Latest papers

451 papers54 papers in the last four weeks, up 69% on the four weeks before. 0.3% of all new papers.

Mar 29, 2026

When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models

Visual-Language Models (VLMs) have demonstrated exceptional cross-modal understanding across various tasks, including zero-shot classification, image captioning, and visual question answering. However, their robustness to physically plausible non-rigid deformations-such as wrinkles on flexible surfaces-remains poorly understood. In this work, we propose a parametric structural perturbation method inspired by the mechanics of three-dimensional fabric wrinkles. Specifically, our method generates photorealistic non-rigid perturbations by constructing multi-scale wrinkle fields and integrating displacement field distortion with surface-consistent appearance variations. To achieve an optimal balance between visual naturalness and adversarial effectiveness, we design a hierarchical fitness function in a low-dimensional parameter space and employ an optimization-based search strategy. We evaluate our approach using a two-stage framework: perturbations are first optimized on a zero-shot classification proxy task and subsequently assessed for transferability on generative tasks. Experimental results demonstrate that our method significantly degrades the performance of various state-of-the-art VLMs, consistently outperforming baselines in both image captioning and visual question-answering tasks.

Chengyin Hu, Xuemeng Sun, Jiaju Han +5

Adversarial Attacks on VLMs Adversarial Attacks VLM Robustness Physical Adversarial Attacks

Mar 29, 2026

Fundamental Limits of Man-in-the-Middle Attack Detection in Model-Free Reinforcement Learning

We consider the problem of learning-based man-in-the-middle (MITM) attacks in cyber-physical systems (CPS), and extend our previously proposed Bellman Deviation Detection (BDD) framework for model-free reinforcement learning (RL). We refine the standard MDP attack model by allowing the reward function to depend on both the current and subsequent states, thereby capturing reward variations induced by errors in the adversary's transition estimate. We also derive an optimal system-identification strategy for the adversary that minimizes detectable value deviations. Further, we prove that the agent's asymptotic learning time required to secure the system scales linearly with the adversary's learning time, and that this matches the optimal lower bound. Hence, the proposed detection scheme is order-optimal in detection efficiency. Finally, we extend the framework to asynchronous and intermittent attack scenarios, where reliable detection is preserved.

Rishi Rani, Massimo Franceschetti

CPS Security Adversarial Attacks Cybersecurity Model-Free RL

Mar 27, 2026

Trustworthy AI-Driven Dynamic Hybrid RIS: Joint Optimization and Reward Poisoning-Resilient Control in Cognitive MISO Networks

Cognitive radio networks (CRNs) are a key mechanism for alleviating spectrum scarcity by enabling secondary users (SUs) to opportunistically access licensed frequency bands without harmful interference to primary users (PUs). To address unreliable direct SU links and energy constraints common in next-generation wireless networks, this work introduces an adaptive, energy-aware hybrid reconfigurable intelligent surface (RIS) for underlay multiple-input single-output (MISO) CRNs. Distinct from prior approaches relying on static RIS architectures, our proposed RIS dynamically alternates between passive and active operation modes in real time according to harvested energy availability. We also model our scenario under practical hardware impairments and cascaded fading channels. We formulate and solve a joint transmit beamforming and RIS phase optimization problem via the soft actor-critic (SAC) deep reinforcement learning (DRL) method, leveraging its robustness in continuous and highly dynamic environments. Notably, we conduct the first systematic study of reward poisoning attacks on DRL agents in RIS-enhanced CRNs, and propose a lightweight, real-time defense based on reward clipping and statistical anomaly filtering. Numerical results demonstrate that the SAC-based approach consistently outperforms established DRL baselines, and that the dynamic hybrid RIS strikes a superior trade-off between throughput and energy consumption compared to fully passive and fully active alternatives. We further show the effectiveness of our defense in maintaining SU performance even under adversarial conditions. Our results advance the practical and secure deployment of RIS-assisted CRNs, and highlight crucial design insights for energy-constrained wireless systems.

Deemah H. Tashman, Soumaya Cherkaoui

LINCS Laboratory, Department of Computer and Software Engineering, Polytechnique Montréal, Montréal, QC, Canada, H3T 1J4

Wireless Communications Reconfigurable Intelligent Surfaces Wireless Resource Allocation Adversarial Attacks RL Control

Mar 27, 2026

PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing

Message Passing Neural Networks (MPNNs) have achieved strong performance on tasks involving relational data. However, small perturbations to graph structure can significantly alter their outputs, raising concerns about their robustness in real-world deployment in security critical environments. In this work, we study a core vulnerability in MPNNs that explicitly consume graph topology via the adjacency matrix or Laplacian as part of their message passing mechanism. We show that this design choice exposes an extremely vulnerable attack surface, with significant effects even under minimal perturbation. Building on this observation, we propose PEA, a simple, gradient-free, black-box injection attack that requires only a single query to the target model, capitalizing on this vulnerability by constructing a perturbation aligned with a specific significant eigenvector to induce large output deviations. Unlike graph modification attacks, PEA operates under the realistic assumption that adversaries cannot alter the original graph and are limited to injecting new nodes at inference time. PEA requires no iterative optimization, parameter learning, or surrogate models---which require additional training and remain susceptible to differences in model priors and generalization capabilities---thereby avoiding significant computational overhead and the associated transferability challenges. We evaluate PEA on popular benchmark datasets across three graph learning tasks, showing consistent performance degradation under realistic attack constraints despite its simplicity. Our results reveal a fundamental security weakness in topology-driven message passing architectures and urge an implementation shift, as the worst effects of such attacks can be substantially mitigated through appropriate input filtering.

Bhavya Kohli, Biplab Sikdar

National University of Singapore, Singapore

Adversarial Attacks Graph Neural Networks Black-Box Adversarial Attacks

Mar 26, 2026

Mitigating Evasion Attacks in Fog Computing Resource Provisioning Through Proactive Hardening

This paper investigates the susceptibility to model integrity attacks that overload virtual machines assigned by the k-means algorithm used for resource provisioning in fog networks. The considered k-means algorithm runs two phases iteratively: offline clustering to form clusters of requested workload and online classification of new incoming requests into offline-created clusters. First, we consider an evasion attack against the classifier in the online phase. A threat actor launches an exploratory attack using query-based reverse engineering to discover the Machine Learning (ML) model (the clustering scheme). Then, a passive causative (evasion) attack is triggered in the offline phase. To defend the model, we suggest a proactive method using adversarial training to introduce attack robustness into the classifier. Our results show that our mitigation technique effectively maintains the stability of the resource provisioning system against attacks.

Younes Salmi, Hanna Bogucka

Institute of Radiocommunications, Poznan University of Technology, Poznań, Poland

Adversarial Attacks

Mar 26, 2026

A Unified Spatial Alignment Framework for Highly Transferable Transformation-Based Attacks on Spatially Structured Tasks

Transformation-based adversarial attacks (TAAs) demonstrate strong transferability when deceiving classification models. However, existing TAAs often perform unsatisfactorily or even fail when applied to structured tasks such as semantic segmentation and object detection. Encouragingly, recent studies that categorize transformations into non-spatial and spatial transformations inspire us to address this challenge. We find that for non-structured tasks, labels are spatially non-structured, and thus TAAs are not required to adjust labels when applying spatial transformations. In contrast, for structured tasks, labels are spatially structured, and failing to transform labels synchronously with inputs can cause spatial misalignment and yield erroneous gradients. To address these issues, we propose a novel unified Spatial Alignment Framework (SAF) for highly transferable TAAs on spatially structured tasks, where the TAAs spatially transform labels synchronously with the input using the proposed Spatial Alignment (SA) algorithm. Extensive experiments demonstrate the crucial role of our SAF for TAAs on structured tasks. Specifically, in non-targeted attacks, our SAF degrades the average mIoU on Cityscapes from 24.50 to 11.34, and on Kvasir-SEG from 49.91 to 31.80, while reducing the average mAP of COCO from 17.89 to 5.25.

Jiaming Liang, Chi-Man Pun

University of Macau

Adversarial Attacks on Object Detectors Adversarial Attacks Adversarial Transferability

Mar 25, 2026

Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting

State-of-the-art crowd counting and localization are primarily modeled using two paradigms: density maps and point regression. Given the field's security ramifications, there is active interest in model robustness against adversarial attacks. Recent studies have demonstrated transferability across density-map-based approaches via adversarial patches, but cross-paradigm attacks (i.e., across both density map-based models and point regression-based models) remain unexplored. We introduce a novel adversarial framework that compromises both density map and point regression architectural paradigms through a comprehensive multi-task loss optimization. For point-regression models, we employ scene-density-specific high-confidence logit suppression; for density-map approaches, we use peak-targeted density map suppression. Both are combined with model-agnostic perceptual constraints to ensure that perturbations are effective and imperceptible to the human eye. Extensive experiments demonstrate the effectiveness of our attack, achieving on average a 7X increase in Mean Absolute Error compared to clean images while maintaining competitive visual quality, and successfully transferring across seven state-of-the-art crowd models with transfer ratios ranging from 0.55 to 1.69. Our approach strikes a balance between attack effectiveness and imperceptibility compared to state-of-the-art transferable attack strategies. The source code is available at https://github.com/simurgh7/CrowdGen

Alabi Mehzabin Anisha, Guangjing Wang, Sriram Chellappan

University of South Florida, Tampa, Florida, USA

Adversarial Attacks Transfer-Based Adversarial Attacks Adversarial Transferability Crowd Counting

Mar 25, 2026

Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage

Deep learning models for time series imputation are now essential in fields such as healthcare, the Internet of Things (IoT), and finance. However, their deployment raises critical privacy concerns. Beyond the well-known issue of unintended memorization, which has been extensively studied in generative models, we demonstrate that time series models are vulnerable to inference attacks in a black-box setting. In this work, we introduce a two-stage attack framework comprising: (1) a novel membership inference attack based on a reference model that improves detection accuracy, even for models robust to overfitting-based attacks, and (2) the first attribute inference attack that predicts sensitive characteristics of the training data for timeseries imputation model. We evaluate these attacks on attention-based and autoencoder architectures in two scenarios: models that are trained from scratch, and fine-tuned models where the adversary has access to the initial weights. Our experimental results demonstrate that the proposed membership attack retrieves a significant portion of the training data with a tpr@top25% score significantly higher than a naive attack baseline. We show that our membership attack also provides a good insight of whether attribute inference will work (with a precision of 90% instead of 78% in the genral case).

Faiz Taleb, Ivan Gazeau, Maryline Laurent

EDF SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France · EDF, 91120 Palaiseau, France · SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris

User Attribute Inference Attacks Membership Inference Attacks Adversarial Attacks Time Series Imputation

Mar 24, 2026

Targeted Adversarial Traffic Generation : Black-box Approach to Evade Intrusion Detection Systems in IoT Networks

The integration of machine learning (ML) algorithms into Internet of Things (IoT) applications has introduced significant advantages alongside vulnerabilities to adversarial attacks, especially within IoT-based intrusion detection systems (IDS). While theoretical adversarial attacks have been extensively studied, practical implementation constraints have often been overlooked. This research addresses this gap by evaluating the feasibility of evasion attacks on IoT network-based IDSs, employing a novel black-box adversarial attack. Our study aims to bridge theoretical vulnerabilities with real-world applicability, enhancing understanding and defense against sophisticated threats in modern IoT ecosystems. Additionally, we propose a defense scheme tailored to mitigate the impact of evasion attacks, thereby reinforcing the resilience of ML-based IDSs. Our findings demonstrate successful evasion attacks against IDSs, underscoring their susceptibility to advanced techniques. In contrast, we proposed a defense mechanism that exhibits robust performance by effectively detecting the majority of adversarial traffic, showcasing promising outcomes compared to current state-of-the-art defenses. By addressing these critical cybersecurity challenges, our research contributes to advancing IoT security and provides insights for developing more resilient IDS.

Islam Debicha, Tayeb Kenaza, Ishak Charfi +3

Adversarial Attacks IoT Intrusion Detection Black-Box Adversarial Attacks Adversarial Example Detection

Mar 24, 2026

PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning

Federated Learning (FL), as a popular distributed learning paradigm, has shown outstanding performance in improving computational efficiency and protecting data privacy, and is widely applied in industrial image classification. However, due to its distributed nature, FL is vulnerable to threats from malicious clients, with poisoning attacks being a common threat. A major limitation of existing poisoning attack methods is their difficulty in bypassing model performance tests and defense mechanisms based on model anomaly detection. This often results in the detection and removal of poisoned models, which undermines their practical utility. To ensure both the performance of industrial image classification and attacks, we propose a targeted poisoning attack, PoiCGAN, based on feature-label collaborative perturbation. Our method modifies the inputs of the discriminator and generator in the Conditional Generative Adversarial Network (CGAN) to influence the training process, generating an ideal poison generator. This generator not only produces specific poisoned samples but also automatically performs label flipping. Experiments across various datasets show that our method achieves an attack success rate 83.97% higher than baseline methods, with a less than 8.87% reduction in the main task's accuracy. Moreover, the poisoned samples and malicious models exhibit high stealthiness.

Tao Liu, Jiguang Lv, Dapeng Man +7

College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, China

Data Poisoning Attacks Adversarial Attacks Federated Learning Generative Adversarial Networks

Mar 21, 2026

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation

Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a universal adversarial patch that generalizes across images and both ViT and CNN architectures without requiring access to target model parameters.

Aarush Aggarwal, Akshat Tomar, Amritanshu Tiwari +1

Data Science Group, Indian Institute of Technology Roorkee, India

Adversarial Patch Attacks Adversarial Attacks Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks

Mar 21, 2026

Adversarial Attacks on Locally Private Graph Neural Networks

Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious concerns, especially when dealing with sensitive information. Local Differential Privacy (LDP) offers a privacy-preserving framework for training GNNs, but its impact on adversarial robustness remains underexplored. This paper investigates adversarial attacks on LDP-protected GNNs. We explore how the privacy guarantees of LDP can be leveraged or hindered by adversarial perturbations. The effectiveness of existing attack methods on LDP-protected GNNs are analyzed and potential challenges in crafting adversarial examples under LDP constraints are discussed. Additionally, we suggest directions for defending LDP-protected GNNs against adversarial attacks. This work investigates the interplay between privacy and security in graph learning, highlighting the need for robust and privacy-preserving GNN architectures.

Matta Varun, Ajay Kumar Dhakar, Yuan Hong +1

Indian Institute of Technology Kharagpur, India · University of Connecticut, USA

Adversarial Attacks Graph Neural Networks Privacy-Preserving ML Differential Privacy

Mar 20, 2026

CAMA: Exploring Collusive Adversarial Attacks in c-MARL

Cooperative multi-agent reinforcement learning (c-MARL) has been widely deployed in real-world applications, such as social robots, embodied intelligence, UAV swarms, etc. Nevertheless, many adversarial attacks still exist to threaten various c-MARL systems. At present, the studies mainly focus on single-adversary perturbation attacks and white-box adversarial attacks that manipulate agents' internal observations or actions. To address these limitations, we in this paper attempt to study collusive adversarial attacks through strategically organizing a set of malicious agents into three collusive attack modes: Collective Malicious Agents, Disguised Malicious Agents, and Spied Malicious Agents. Three novelties are involved: i) three collusive adversarial attacks are creatively proposed for the first time, and a unified framework CAMA for policy-level collusive attacks is designed; ii) the attack effectiveness is theoretically analyzed from the perspectives of disruptiveness, stealthiness, and attack cost; and iii) the three collusive adversarial attacks are technically realized through agent's observation information fusion, attack-trigger control. Finally, multi-facet experiments on four SMAC II maps are performed, and experimental results showcase the three collusive attacks have an additive adversarial synergy, strengthening attack outcome while maintaining high stealthiness and stability over long horizons. Our work fills the gap for collusive adversarial learning in c-MARL.

Men Niu, Xinxin Fan, Quanliang Jing +2

Institute of Computing Technology, CAS · UCAS · Beihang University

Adversarial Attacks Adversarial MARL Multi-Agent System Security Multi-Agent Reinforcement Learning Cooperative MARL

Mar 19, 2026

Robustness, Cost, and Attack-Surface Concentration in Phishing Detection

Phishing detectors built on engineered website features attain near-perfect accuracy under i.i.d.\ evaluation, yet deployment security depends on robustness to post-deployment feature manipulation. We study this gap through a cost-aware evasion framework that models discrete, monotone feature edits under explicit attacker budgets. Three diagnostics are introduced: minimal evasion cost (MEC), the evasion survival rate

S(B)

, and the robustness concentration index (RCI). On the UCI Phishing Websites benchmark (11,055 instances, 30 ternary features), Logistic Regression, Random Forests, Gradient Boosted Trees, and XGBoost all achieve

\mathrm{AUC}\ge 0.979

under static evaluation. Under budgeted sanitization-style evasion, robustness converges across architectures: the median MEC equals 2 with full features, and over 80% of successful minimal-cost evasions concentrate on three low-cost surface features. Feature restriction improves robustness only when it removes all dominant low-cost transitions. Under strict cost schedules, infrastructure-leaning feature sets exhibit 17-19% infeasible mass for ensemble models, while the median MEC among evadable instances remains unchanged. We formalize this convergence: if a positive fraction of correctly detected phishing instances admit evasion through a single feature transition of minimal cost

c_{\min}

, no classifier can raise the corresponding MEC quantile above

c_{\min}

without modifying the feature representation or cost model. Adversarial robustness in phishing detection is governed by feature economics rather than model complexity.

Julian Allagan, Mohamed Elbakary, Zohreh Safari +4

Department of Mathematics, Computer Science, and Engineering Technology Elizabeth City State University, Elizabeth City, NC 27909, USA

Phishing Detection Adversarial Robustness Adversarial Attacks

Mar 19, 2026

On Optimizing Multimodal Jailbreaks for Spoken Language Models

As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where adversarial prompts induce harmful responses. Yet existing attacks largely remain unimodal, optimizing either text or audio in isolation. We explore gradient-based multimodal jailbreaks by introducing JAMA (Joint Audio-text Multimodal Attack), a joint multimodal optimization framework combining Greedy Coordinate Gradient (GCG) for text and Projected Gradient Descent (PGD) for audio, to simultaneously perturb both modalities. Evaluations across four state-of-the-art SLMs and four audio types demonstrate that JAMA surpasses unimodal jailbreak rate by 1.5x to 20x. We analyze the operational dynamics of this joint attack and show that a sequential approximation method makes it 4x to 6x faster. Our findings suggest that unimodal safety is insufficient for robust SLMs. The code and data are available at https://repos.lsv.uni-saarland.de/akrishnan/multimodal-jailbreak-slm.

Aravind Krishnan, Karolina Stańczak, Dietrich Klakow

Saarland University, Germany · DFKI GmbH, Saarbrücken, Germany · ETH AI Center, Switzerland

Adversarial Attacks LLM Jailbreak Attacks Multimodal Jailbreak Attacks Speech Language Models

Mar 19, 2026

Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks

Graph neural networks (GNNs) are widely used for learning from graph-structured data in domains such as social networks, recommender systems, and financial platforms. To comply with privacy regulations like the GDPR, CCPA, and PIPEDA, approximate graph unlearning, which aims to remove the influence of specific data points from trained models without full retraining, has become an increasingly important component of trustworthy graph learning. However, approximate unlearning often incurs subtle performance degradation, which may incur negative and unintended side effects. In this work, we show that such degradations can be amplified into adversarial attacks. We introduce the notion of unlearning corruption attacks, where an adversary injects carefully chosen nodes into the training graph and later requests their deletion. Because deletion requests are legally mandated and cannot be denied, this attack surface is both unavoidable and stealthy: the model performs normally during training, but accuracy collapses only after unlearning is applied. Technically, we formulate this attack as a bi-level optimization problem: to overcome the challenges of black-box unlearning and label scarcity, we approximate the unlearning process via gradient-based updates and employ a surrogate model to generate pseudo-labels for the optimization. Extensive experiments across benchmarks and unlearning algorithms demonstrate that small, carefully designed unlearning requests can induce significant accuracy degradation, raising urgent concerns about the robustness of GNN unlearning under real-world regulatory demands. The source code will be released upon paper acceptance.

Jiahao Zhang, Yilong Wang, Suhang Wang

The Pennsylvania State University University Park, PA, USA

Graph Unlearning Adversarial Attacks Graph Neural Networks Machine Unlearning

Mar 17, 2026

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models

Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generation of offensive content. Image Generation Model Unlearning (IGMU) mitigates these risks by removing harmful concepts without full retraining. Despite growing attention, the robustness under adversarial inputs, particularly image-side threats in black-box settings, remains underexplored. To bridge this gap, we present REFORGE, a black-box red-teaming framework that evaluates IGMU robustness via adversarial image prompts. REFORGE initializes stroke-based images and optimizes perturbations with a cross-attention-guided masking strategy that allocates noise to concept-relevant regions, balancing attack efficacy and visual fidelity. Extensive experiments across representative unlearning tasks and defenses demonstrate that REFORGE significantly improves attack success rate while achieving stronger semantic alignment and higher efficiency than involved baselines. These results expose persistent vulnerabilities in current IGMU methods and highlight the need for robustness-aware unlearning against multi-modal adversarial attacks. Our code is at: https://github.com/Imfatnoily/REFORGE.

Yong Zou, Haoran Li, Fanxiao Li +5

Yunnan University · Northeastern University · National University of Singapore

Adversarial Attacks Adversarial Robustness Diffusion Model Unlearning Black-Box Adversarial Attacks Adversarial Prompt Generation

Mar 16, 2026

AI Evasion and Impersonation Attacks on Facial Re-Identification with Activation Map Explanations

Facial identification systems are increasingly deployed in surveillance and yet their vulnerability to adversarial evasion and impersonation attacks pose a critical risk. This paper introduces a novel framework for generating adversarial patches capable of both evasion and impersonation attacks against deep re-identification models across non-overlapping cameras. Unlike prior approaches that require iterative patch optimisation for each target, our method employs a conditional encoder-decoder network to synthesize adversarial patches in a single forward pass, guided by multi-scale features from source and target images. The patches are optimised with a dual adversarial objective comprising of pull and push terms. To enhance imperceptibility and aid physical deployment, we further integrate naturalistic patch generation using pre-trained latent diffusion models. Experiments on standard pedestrian (Market-1501, DukeMTMCreID) and facial recognition benchmarks (CelebA-HQ, PubFig) datasets demonstrate the effectiveness of the proposed method. Our adversarial evasion attacks reduce mean Average Precision from 90% to 0.4% in white-box settings and from 72% to 0.4% in black-box settings, showing strong cross-model generalization. In targeted impersonation attacks, our framework achieves a success rate of 27% on CelebA-HQ, competing with other patch-based methods. We go further to use clustering of activation maps to interpret which features are most used by adversarial attacks and propose a pathway for future countermeasures. The results highlight the practicality of adversarial patch attacks on retrieval-based systems and underline the urgent need for robust defense strategies.

Noe Claudel, Weisi Guo, Yang Xing

All authors are with the Centre for Assured and Connected Autonomy, Cranfield University, Bedford, UK.

Adversarial Attacks Adversarial Patch Attacks Black-Box Adversarial Attacks

Mar 16, 2026

Hijacking online reviews: sparse manipulation and behavioral buffering in popularity-biased rating systems

Online reviews and recommendation systems help users navigate overwhelming choice, but they are vulnerable to self-reinforcing distortions. This paper examines how a single malicious reviewer can exploit popularity-biased rating dynamics and whether behavioral heterogeneity in user responses can reduce the damage. We develop a minimal agent-based model in which users choose what to rate partly on the basis of currently displayed averages. We compare broad attacks that perturb many items with sparse attacks that selectively boost low-quality items and suppress high-quality items. Additional analyses not shown here indicate that sparse attacks are substantially more harmful than broad attacks because they better exploit popularity-based exposure. The main text then focuses on sparse attacks and asks how their effects change as the fraction of contrarian users increases. Three results stand out. First, attack-induced damage is strongest when prior honest reviews are scarce, revealing a transition from a fragile low-information regime to a more robust high-information regime. Second, sparse attacks are especially effective at artificially promoting low-quality items. Third, moderate contrarian diversity partially buffers these distortions, primarily by suppressing the rise of low-quality items rather than fully restoring high-quality items to the top. The findings suggest that recommendation robustness depends not only on attack detection and predictive accuracy, but also on review density, popularity feedback, and user response heterogeneity.

Itsuki Fujisaki, Kunhao Yang

College of Knowledge and Library Science, School of Informatics, Tsukuba University, Ibaraki, Japan · College of Engineering, Shibaura Institute of Technology; Tokyo, Japan

Popularity Bias in Recommender Systems Recommender Systems Adversarial Attacks Popularity Bias

Mar 16, 2026

Architecture-Agnostic Feature Synergy for Universal Defense Against Heterogeneous Generative Threats

Generative AI deployment poses unprecedented challenges to content safety and privacy. However, existing defense mechanisms are often tailored to specific architectures (e.g., Diffusion Models or GANs), creating fragile "defense silos" that fail against heterogeneous generative threats. This paper identifies a fundamental optimization barrier in naive pixel-space ensemble strategies: due to divergent objective functions, pixel-level gradients from heterogeneous generators become statistically orthogonal, causing destructive interference. To overcome this, we observe that despite disparate low-level mechanisms, high-level feature representations of generated content exhibit alignment across architectures. Based on this, we propose the Architecture-Agnostic Targeted Feature Synergy (ATFS) framework. By introducing a target guidance image, ATFS reformulates multi-model defense as a unified feature space alignment task, enabling intrinsic gradient alignment without complex rectification. Extensive experiments show ATFS achieves SOTA protection in heterogeneous scenarios (e.g., Diffusion+GAN). It converges rapidly, reaching over 90% performance within 40 iterations, and maintains strong attack potency even under tight perturbation budgets. The framework seamlessly extends to unseen architectures (e.g., VQ-VAE) by switching the feature extractor, and demonstrates robust resistance to JPEG compression and scaling. Being computationally efficient and lightweight, ATFS offers a viable pathway to dismantle defense silos and enable universal generative security. Code and models are open-sourced for reproducibility.

Bingxue Zhang, Yang Gao, Feida Zhu +2

University of Shanghai for Science and Technology, Shanghai, China · Singapore Management University, Singapore, Singapore · Shanghai Jiao Tong University, Shanghai, China

Adversarial Attacks Adversarial Perturbations

Mar 16, 2026

Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents

Computer-using agents (CUAs) act directly on graphical user interfaces, yet their perception of the screen is often unreliable. Existing work largely treats these failures as performance limitations, asking whether an action succeeds, rather than whether the agent is acting on the correct object at all. We argue that this is fundamentally a security problem. We formalize the visual confused deputy: a failure mode in which an agent authorizes an action based on a misperceived screen state, due to grounding errors, adversarial screenshot manipulation, or time-of-check-to-time-of-use (TOCTOU) races. This gap is practically exploitable: even simple screen-level manipulations can redirect routine clicks into privileged actions while remaining indistinguishable from ordinary agent mistakes. To mitigate this threat, we propose the first guardrail that operates outside the agent's perceptual loop. Our method, dual-channel contrastive classification, independently evaluates (1) the visual click target and (2) the agent's reasoning about the action against deployment-specific knowledge bases, and blocks execution if either channel indicates risk. The key insight is that these two channels capture complementary failure modes: visual evidence detects target-level mismatches, while textual reasoning reveals dangerous intent behind visually innocuous controls. Across controlled attacks, real GUI screenshots, and agent traces, the combined guardrail consistently outperforms either channel alone. Our results suggest that CUA safety requires not only better action generation, but independent verification of what the agent believes it is clicking and why. Materials are provided\footnote{Model, benchmark, and code: https://github.com/vllm-project/semantic-router}.

Xunzhuo Liu, Bowei He, Xue Liu +3

vLLM Semantic Router Project · MBZUAI · McGill University +2

Computer-Use Agent Safety AI Agent Security Computer-Use Agents Software Security Runtime Enforcement for AI Agents Adversarial Attacks

Mar 14, 2026

Benchmarking the Energy Cost of Assurance in Neuromorphic Edge Robotics

Deploying trustworthy artificial intelligence on edge robotics imposes a difficult trade-off between high-assurance robustness and energy sustainability. Traditional defense mechanisms against adversarial attacks typically incur significant computational overhead, threatening the viability of power-constrained platforms in environments such as cislunar space. This paper quantifies the energy cost of assurance in event-driven neuromorphic systems. We benchmark the Hierarchical Temporal Defense (HTD) framework on the BrainChip Akida AKD1000 processor against a suite of adversarial temporal attacks. We demonstrate that unlike traditional deep learning defenses which often degrade efficiency significantly with increased robustness, the event-driven nature of the proposed architecture achieves a superior trade-off. The system reduces gradient-based adversarial success rates from 82.1% to 18.7% and temporal jitter success rates from 75.8% to 25.1%, while maintaining an energy consumption of approximately 45 microjoules per inference. We report a counter-intuitive reduction in dynamic power consumption in the fully defended configuration, attributed to volatility-gated plasticity mechanisms that induce higher network sparsity. These results provide empirical evidence that neuromorphic sparsity enables sustainable and high-assurance edge autonomy.

Sylvester Kaczmarek

Department of Computing, Imperial College London, London, United Kingdom

Adversarial Robustness Neuromorphic Computing Energy-Efficient ML Robotics Adversarial Attacks

Mar 14, 2026

Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs

Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert prompt-based attacks against speech-driven LLMs under realistic black-box conditions using commodity hardware. SWhisper enables robust, inaudible delivery of arbitrary target baseband audio-including long and structured prompts-on commodity devices by encoding it into near-ultrasound waveforms that demodulate faithfully after acoustic transmission and microphone nonlinearity. This is achieved through a simple yet effective approach to modeling nonlinear channel characteristics across devices and environments, combined with lightweight channel-inversion pre-compensation. Building on this high-fidelity covert channel, we design a voice-aware jailbreak generation method that ensures intelligibility, brevity, and transferability under speech-driven interfaces. Experiments across both commercial and open-source speech-driven LLMs demonstrate strong black-box effectiveness. On commercial models, SWhisper achieves up to 0.94 non-refusal (NR) and 0.925 specific-convincing (SC). A controlled user study further shows that the injected jailbreak audio is perceptually indistinguishable from background-only playback for human listeners. Although jailbreaks serve as a case study, the underlying covert acoustic channel enables a broader class of high-fidelity prompt-injection and commandexecution attacks.

Zijian Ling, Pingyi Hu, Xiuyong Gao +6

School of Cyber Science and Engineering, Huazhong University of Science and Technology · State Key Laboratory of Internet Architecture, Tsinghua University · Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology +1

Adversarial Attacks LLM Security Prompt Injection Attacks on LLMs Jailbreak Attacks Speech Language Models

Mar 13, 2026

Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting

Recent advances in 3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface, the resource-targeting attack. This attack poisons training images, excessively inducing Gaussian growth to cause resource exhaustion. Although efficiency-oriented methods such as smoothing, thresholding, and pruning have been explored, these spatial-domain strategies operate on visible structures but overlook how stealthy perturbations distort the underlying spectral behaviors of training data. As a result, poisoned inputs introduce abnormal high-frequency amplifications that mislead 3DGS into interpreting noisy patterns as detailed structures, ultimately causing unstable Gaussian overgrowth and degraded scene fidelity. To address this, we propose Spectral Defense in Gaussian and image fields. We first design a 3D frequency filter to selectively prune Gaussians exhibiting abnormally high frequencies. Since natural scenes also contain legitimate high-frequency structures, directly suppressing high frequencies is insufficient, and we further develop a 2D spectral regularization on renderings, distinguishing naturally isotropic frequencies while penalizing anisotropic angular energy to constrain noisy patterns. Experiments show that our defense builds robust, accurate, and secure 3DGS, suppressing overgrowth by up to

5.92\times

, reducing memory by up to

3.66\times

, and improving speed by up to

4.34\times

under attacks.

Yang Chen, Yi Yu, Jiaming He +3

Nanyang Technological University · UESTC · Tsinghua University +2

3D Gaussian Splatting Adversarial Robustness Adversarial Attacks 3D Gaussian Pruning Spectral Regularization

Mar 13, 2026

CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models

Diffusion-based image-to-video (I2V) models increasingly exhibit world-model-like properties by implicitly capturing temporal dynamics. However, existing studies have mainly focused on visual quality and controllability, and the robustness of the state transition learned by the model remains understudied. To fill this gap, we are the first to analyze the vulnerability of I2V models, find that temporal control mechanisms constitute a new attack surface, and reveal the challenge of modeling them uniformly under different attack settings. Based on this, we propose a trajectory-control attack, called CtrlAttack, to interfere with state evolution during the generation process. Specifically, we represent the perturbation as a low-dimensional velocity field and construct a continuous displacement field via temporal integration, thereby affecting the model's state transitions while maintaining temporal consistency; meanwhile, we map the perturbation to the observation space, making the method applicable to both white-box and black-box attack settings. Experimental results show that even under low-dimensional and strongly regularized perturbation constraints, our method can still significantly disrupt temporal consistency by increasing the attack success rate (ASR) to over 90% in the white-box setting and over 80% in the black-box setting, while keeping the variation of the FID and FVD within 6 and 130, respectively, thus revealing the potential security risk of I2V models at the level of state dynamics.

Shuhan Xu, Siyuan Liang, Hongling Zheng +4

Wuhan University · Nanyang Technological University · Beijing Institute of Technology

Adversarial Attacks Image-to-Video Generation Temporal Consistency in Video Generation Controllable Video Generation

Mar 12, 2026

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models

Backdoor attacks against pre-trained models (PTMs) have traditionally operated under an ``immediacy assumption,'' where malicious behavior manifests instantly upon trigger occurrence. This work revisits and challenges this paradigm by introducing Delayed Backdoor Attacks (DBA), a new class of threats in which activation is temporally decoupled from trigger exposure. We propose that this temporal dimension is the key to unlocking a previously infeasible class of attacks: those that use common, everyday words as triggers. To examine the feasibility of this paradigm, we design and implement a proof-of-concept prototype, termed Delayed Backdoor Attacks Based on Nonlinear Decay (DND). DND embeds a lightweight, stateful logic module that postpones activation until a configurable threshold is reached, producing a distinct latency phase followed by a controlled outbreak. We derive a formal model to characterize this latency behavior and propose a dual-metric evaluation framework (ASR and ASR

_{delay}

) to empirically measure the delay effect. Extensive experiments on four (natural language processing)NLP benchmarks validate the core capabilities of DND: it remains dormant for a controllable duration, sustains high clean accuracy (

\ge

94%), and achieves near-perfect post-activation attack success rates (

\approx

99%, The average of other methods is below 95%.). Moreover, DND exhibits resilience against several state-of-the-art defenses. This study provides the first empirical evidence that the temporal dimension constitutes a viable yet unprotected attack surface in PTMs, underscoring the need for next-generation, stateful, and time-aware defense mechanisms.

Zikang Ding, Haomiao Yang, Meng Hao +6

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Sichuan 611731, China · Singapore Management University · School of Computer Science, Xi’an Polytechnic University, Xi’an 710048, China. +1

Adversarial Attacks Backdoor Attacks

Mar 11, 2026

Backdoor Directions in Vision Transformers

This paper investigates how Backdoor Attacks are represented within Vision Transformers (ViTs). By assuming knowledge of the trigger, we identify a specific ``trigger direction'' in the model's activations that corresponds to the internal representation of the trigger. We confirm the causal role of this linear direction by showing that interventions in both activation and parameter space consistently modulate the model's backdoor behavior across multiple datasets and attack types. Using this direction as a diagnostic tool, we trace how backdoor features are processed across layers. Our analysis reveals distinct qualitative differences: static-patch triggers follow a different internal logic than stealthy, distributed triggers. We further examine the link between backdoors and adversarial attacks, specifically testing whether PGD-based perturbations (de-)activate the identified trigger mechanism. Finally, we propose a data-free, weight-based detection scheme for stealthy-trigger attacks. Our findings show that mechanistic interpretability offers a robust framework for diagnosing and addressing security vulnerabilities in computer vision.

Sengim Karayalcin, Marina Krcek, Pin-Yu Chen +1

Leiden University · Radboud University · IBM Research +1

Backdoor Detection Vision Transformer Adversarial Robustness Adversarial Attacks

Mar 11, 2026

Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?

Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the model. Such methods, although they remain empirically effective, usually do not guarantee that an adversarial example can be found for a particular model. In this paper, we propose Contract And Conquer (CAC), an approach to provably compute adversarial examples for neural networks in a black-box manner. The method is based on knowledge distillation of a black-box model on an expanding distillation dataset and precise contraction of the adversarial example search space. CAC is supported by the transferability guarantee: we prove that the method yields an adversarial example for the black-box model within a fixed number of algorithm iterations. Experimentally, we demonstrate that the proposed approach outperforms existing state-of-the-art black-box attack methods on ImageNet dataset for different target models, including vision transformers.

Anna Chistyakova, Mikhail Pautov

Trusted AI Research Center, RAS · AXXX

Adversarial Attacks Black-Box Adversarial Attacks Adversarial Transferability

Mar 11, 2026

Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks

Adversarial examples can represent a serious threat to machine learning (ML) algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems (NIDS), they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS towards adversarial attacks. To that end, we explore two adversarial methods for generating malicious network traffic. The first method is based on Generative Adversarial Networks (GAN) and the second one is the Fast Gradient Sign Method (FGSM). The adversarial examples generated by these methods are then used to evaluate a novel multilayer defense mechanism, specifically designed to mitigate the vulnerability of ML-based NIDS. Our solution consists of one layer of stacking classifiers and a second layer based on an autoencoder. If the incoming network data are classified as benign by the first layer, the second layer is activated to ensure that the decision made by the stacking classifier is correct. We also incorporated adversarial training to further improve the robustness of our solution. Experiments on two datasets, namely UNSW-NB15 and NSL-KDD, demonstrate that the proposed approach increases resilience to adversarial attacks.

Nasim Soltani, Shayan Nejadshamsi, Zakaria Abou El Houda +4

Institut national de la recherche scientifique (INRS-EMT), Université du Québec, Montréal, Québec, Canada · INRS-UQO Mixed Research Unit on Cybersecurity, Gatineau, Québec, Canada · Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montréal, Québec, Canada +2

Network Intrusion Detection Adversarial Robustness Adversarial Attacks

Mar 9, 2026

NetDiffuser: Deceiving DNN-Based Network Attack Detection Systems with Diffusion-Generated Adversarial Traffic

Deep learning (DL)-based Network Intrusion Detection System (NIDS) has demonstrated great promise in detecting malicious network traffic. However, they face significant security risks due to their vulnerability to adversarial examples (AEs). Most existing adversarial attacks maliciously perturb data to maximize misclassification errors. Among AEs, natural adversarial examples (NAEs) are particularly difficult to detect because they closely resemble real data, making them challenging for both humans and machine learning models to distinguish from legitimate inputs. Creating NAEs is crucial for testing and strengthening NIDS defenses. This paper proposes NetDiffuser1, a novel framework for generating NAEs capable of deceiving NIDS. NetDiffuser consists of two novel components. First, a new feature categorization algorithm is designed to identify relatively independent features in network traffic. Perturbing these features minimizes changes while preserving network flow validity. The second component is a novel application of diffusion models to inject semantically consistent perturbations for generating NAEs. NetDiffuser performance was extensively evaluated using three benchmark NIDS datasets across various model architectures and state-of-the-art adversarial detectors. Our experimental results show that NetDiffuser achieves up to a 29.93% higher attack success rate and reduces AE detection performance by at least 0.267 (in some cases up to 0.534) in the Area under the Receiver Operating Characteristic Curve (AUC-ROC) score compared to the baseline attacks.

Pratyay Kumar, Abu Saleh Md Tayeen, Satyajayant Misra +4

Department of Computer Science, New Mexico State University, Las Cruces, NM, USA · University of Hartford, CT, USA · DEVCOM Analysis Center, WSMR, NM, USA

Adversarial Attacks Adversarial Examples Network Intrusion Detection