Transfer-Based Adversarial Attacks

Overview

Transfer-based adversarial attacks study how to craft adversarial inputs using a surrogate model that also fool unseen target models, often when those targets are black boxes. Common approaches use gradient-based optimization, surrogate ensembles, input transformations, or alignment of semantic and intermediate features to reduce overfitting to one model. The methods span image classifiers, object detectors, speech systems, and vision-language models, with work also exploring physical patches and constraints on perceptual quality. A central challenge is that gains depend on how well the surrogate matches the target, so transfer success can vary across architectures and settings, making careful source–target evaluation essential.

Latest papers

90 papers8 papers in the last four weeks, down 27% on the four weeks before. 0.1% of all new papers.

Nov 11, 2026

Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer

Speech tokenizers serve as speech front ends, encoding input speech signals into representations for downstream models, such as automatic speech recognition (ASR) systems and large audio-language models (LALMs). In this paper, we find that speech tokenizers are fragile at the semantic level: small perturbations can disrupt their semantic encoding process and consequently cause severe degradation in downstream ASR and LALM performance. To study this vulnerability, we propose T-SemAttack, a transferable semantic attack based on a semantic encoder ensemble. By jointly drifting the representation spaces of multiple semantic encoders, T-SemAttack effectively disrupts the semantic content of speech while preserving perceptual quality, thereby inducing error features. We further analyze layer-wise representation drift and cross-model gradient alignment. Our findings show that perturbations can induce substantial shifts in deep semantic representations and that the input gradients of different surrogate encoders exhibit directional alignment. These observations suggest that shared adversarially sensitive directions in the input space may be a key factor underlying cross-model attack transferability. Building on these, we introduce ROSETok, a robust speech tokenizer that combines noisy training with robust semantic distillation to improve reconstruction fidelity and downstream SpeechLLM robustness. Extensive experiments on multiple datasets, 9 open-source and black-box ASR systems, and 4 LALMs demonstrate that T-SemAttack achieves strong transferable attack performance, while the proposed Robust Speech Tokenizer exhibits robustness under high-fidelity reconstruction and downstream tasks. Our code and demo are available at https://wxzyd123.github.io/t-semattack.
Nov 8, 2026

Query-Only Prompt-Agnostic Attacks on Visual In-Context Learning

Visual In-Context Learning (VICL) enables promptable segmentation by conditioning RGB predictions on visual demonstrations, making it attractive for auto-labeling, but its robustness under query-only access and unknown deployment prompts remains underexplored. We study query-only, prompt-agnostic targeted attacks where the attacker observes only returned RGB outputs, without access to model internals or deployment prompts. Treating prompt-conditioned RGB rendering as a distinct attack surface, we introduce two appearance-space attacks: Color Hijack (CH) drives foreground colors toward the background to suppress visibility, while Task Hijack (TH) collapses instance-distinguishing colors toward a shared color assignment. To transfer across unseen prompts, we propose a Self-Prompt Surrogate (SPS) constructed from the clean query and its output. In a paired, matched-budget SegGPT comparison, SPS outperforms the Random-Prompt Surrogate (RPS), reducing CH instance foreground retention from 0.918 to 0.155 and TH palette-aware tolerance distance from 0.345 to 0.225. Across four VICL models on COCO and HierText, CH suppresses foregrounds across semantic-, instance-, and text-style outputs, while TH collapses instance colors under held-out deployment prompts. After palette-based decoding, TH also reduces the decoded instance count and mask retention while increasing instance merges. Finally, at 30% corruption, CH-corrupted annotations from a publicly accessible VICL-based auto-labeling pipeline reduce downstream YOLO-seg mAP50 from 0.761 to 0.281.
Nov 6, 2026

Zero-Query Transferable Pretend Benign Attacks with Amortized Online Generation for Cooperative Perception

Cooperative perception enables an ego agent to acquire information from collaborators beyond its own sensors' reach. Yet, the most beneficial messages are often the hardest to verify from local observations. Pretend Benign (PB) exploits this asymmetry by targeting regions with weak local verifiability and applying multi-objective perturbations, making harmful feature changes appear to be benign assistance. However, PB is victim-dependent: selecting regions and optimizing perturbations require the victim model's architecture, parameters, and gradients, limiting transfer to unseen victims. A transferable attack must capture properties shared across cooperative detection models rather than those specific to one network. We address this by building a victim-agnostic attack from a heterogeneous ensemble of surrogate models and encoding its capabilities in a reusable dictionary to reduce per-message generation cost. Specifically, Transferable Pretend Benign (TrPB) transfers PB's region selection criterion and multi-objective perturbation strategy across heterogeneous surrogates to construct an offline attack. We further propose RT-TrPB, which encodes transferable regions and perturbation patterns into a region predictor and reusable perturbation dictionary, amortizing per-message attack generation. Experiments on widely used cooperative perception benchmarks show that RT-TrPB bypasses the consensus-based defenses ROBOSAC and FLD with success rates approaching 100% and generates each perturbation in under 56 ms. To counter PB-style attacks masquerading as benign collaboration, we also propose STTrust, which verifies received messages using spatial and temporal consistency and incorporates identity-level trust. STTrust detects over 90% of PB-style attacks and restores perception performance to near the attack-free level.
Oct 28, 2026

FGSM Attack Transferability from Simulation to Quantum Hardware in Network Intrusion Detection

Quantum computers are now available through cloud platforms, and recent work has proposed using them to detect network intrusions. It is not yet clear how easily such systems can be attacked. We train a hybrid variational quantum classifier (VQC) on the Friday DDoS subset of CICIDS2017 and test it against two attacks: label flipping during training and FGSM evasion at prediction time. We run the tests in simulation and on IBM hardware, the Fez superconducting processor (Heron r2). We find that two models with similar accuracy can differ greatly in how easily they are attacked. A model that decides with little confidence loses half its detections to a very small change in the input, while a model trained to decide with more confidence needs a much larger change before it fails. Attacks built in simulation against the more confident model also work on real hardware, and the device classifies every unaltered attack sample correctly. Simulated device noise does not reduce accuracy, but it does reduce the model's confidence and makes attacks easier, so accuracy alone does not show how exposed a model is. Label flipping has no measurable effect until 15% of attack labels are changed. These results show that device noise should not be treated as a defense and that reported weaknesses in these classifiers depend partly on how they were trained.
Oct 27, 2026

Where Can We Fool the Model's Mind? Response-Guided Semantic Probing and Adaptive Routing for Transferable Attacks on Black-Box MLLMs

Multimodal Large Language Models (MLLMs) ground language in visual evidence, yet their semantic reasoning can be exploited through transferable black-box adversarial attacks. Existing attacks typically allocate perturbations using surrogate-model saliency, which may not reflect how an unseen MLLM semantically interprets or relies on different image regions. We introduce VISTA (Vulnerability-Informed Semantic Transfer Attacks), a black-box framework that identifies semantically vulnerable visual regions from an MLLM's responses without access to gradients, logits, parameters, or internal representations. VISTA supports two attack settings: (i) VISTA-Proxy, a pure-transfer setting that probes an open-source MLLM and transfers the resulting adversarial examples to unseen commercial MLLMs without querying them; and (ii) VISTA-Victim, a query-assisted setting that probes the target MLLM to capture model-specific semantic vulnerabilities. VISTA builds an Uncertainty-Based Multimodal Behavior (UBMB) map from response drift, conflict, misleading, and semantic shifts, then uses entropy-adaptive Sinkhorn routing and a surrogate ensemble to focus perturbations on vulnerable regions. Across GPT-5, Gemini-3.5-Flash, and Claude Sonnet 4.6, VISTA achieves up to 97 % attack success rate (ASR) while maintaining a Peak Signal-to-Noise Ratio (PSNR) above 30 dB. Notably, VISTA-Proxy achieves up to 93 % ASR without querying the final victim, demonstrating that response-derived semantic vulnerability can enable effective transfer across heterogeneous MLLMs.
Oct 23, 2026

Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving

Modern autonomous driving systems widely adopt multi-view Bird's-Eye-View (BEV) based 3D perception models due to their superior performance. Despite their success, the robustness of these models against adversarial camouflage attacks remains largely unexplored. Existing camouflage attacks primarily target single-view 2D detectors, limiting their effectiveness in multi-view 3D perception settings. To address this gap, we propose BEVCA, a novel adversarial camouflage generation framework tailored for multi-view BEV-based 3D perception. Our framework integrates a BEV-feature-based adversarial loss with a multi-view neural rendering module, enabling effective and transferable camouflage attacks across different models and tasks. Extensive experiments in both digital and physical settings demonstrate that BEVCA outperforms state-of-the-art baselines and exhibits strong robustness under real-world conditions. Our code is available at https://github.com/WAVE-AT-IDEA/BEVCA.
Oct 22, 2026

MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition

Despite recent advances, deepfake detectors remain vulnerable to adversarial examples, particularly in diverse, real-world settings. We propose MIG-COW, a novel adversarial attack framework that generates highly generalizable and visually imperceptible adversarial examples. By combining momentum-integrated gradients with a consensus-orthogonal decomposition, MIG-COW captures both shared and model-specific vulnerabilities across heterogeneous CNN and ViT detectors. On the AADD-2025 Challenge benchmarks, MIG-COW achieves a 99.96% white-box attack success rate (ASR) with high perceptual similarity (SSIM), significantly outperforming existing baselines. However, its limited 7.16% ASR against official black-box targets - despite achieving the best overall score - highlights the ongoing challenge of transferability. We also demonstrate that incorporating low-performing but diverse models in the ensemble can degrade attack effectiveness, underscoring the need for careful surrogate model selection in real-world adversarial settings.
Oct 20, 2026

Bridging Digital Deception and Physical Fidelity: A Spatio-Temporal Attack on Cognitive Radars

As cognitive radars evolve towards the end-to-end processing of one-dimensional complex baseband sequences, deep networks face severe adversarial threats. However, existing attacks encounter dual limitations in practical electronic warfare: low cross-architecture transferability and severe vulnerability to physical channel distortions, which degrades their tactical reliability. To overcome these bottlenecks, we propose a physical prior-driven Segmented Spatio-Temporal Attack (SSTA). First, a global-local feature decoupling segmentation mechanism interrupts the adversarial gradients' dependence on long-range sequence coherence, bridging the cross-architecture feature gap. Second, moving beyond static norm constraints devoid of physical semantics, we abstract channel distortions into differentiable spatio-temporal operators, integrating them into momentum iterations via an Expectation over Transformation (EoT) strategy. Comprehensive cross-evaluations across 9 heterogeneous models spanning CNNs, RNNs, and Transformers demonstrate that SSTA outperforms the state-of-the-art baseline by 10.36% in Average Black-Box Attack Success Rate. Furthermore, baseband equivalent simulations confirm that the generated waveforms survive extreme physical distortions and, after matched filtering, achieve zero main-lobe attenuation (0 dB) with noise floor lift strictly within Constant False Alarm Rate tolerances. SSTA successfully unifies digital-domain deception and physical-domain fidelity, providing crucial support for CEW security assessment.
Oct 18, 2026

Tricking Synthetic Image Detectors with Amortized Generative Attacks

Rapid advances in image synthesis have increased the need for reliable synthetic-image detectors, yet their robustness to transferable attacks remains incomplete and understudied. Existing evaluations generally examine whether an attack constructed against one detector transfers to another, but rarely isolate how its effectiveness changes when the attacked images originate from different generators. We conduct a systematic evaluation of three representative attacks: two iterative perturbation-based methods, MIG and MuMoDIG, and the amortized generative attack Tricker. Across four detectors and five generators spanning diverse architectures, we introduce a two-axis evaluation protocol that independently varies the surrogate detector used to construct or train the attack and the generator supplying its input images. We assess attack effectiveness, cross-detector transferability, perceptual quality, runtime, and interaction with common post-processing operations. We revisit Tricker and show that its data and training requirements can be substantially reduced, enabling broader and more efficient evaluation. Our results demonstrate that transferability is not a detector-only property: the input-generator distribution strongly influences both evasion effectiveness and attacked-image quality. MIG and MuMoDIG exhibit pronounced dependence on the detector--generator pair, whereas Tricker provides more uniform white-box evasion and image quality. We additionally observe that post-processing maintains the asymmetric transferability topology. These findings expose a neglected dimension of attack evaluation and motivate transfer-aware protocols that jointly account for detector and generator variation. We will release our code, evaluation data, and trained attack models with a responsible-use statement.
Oct 6, 2026

Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving

The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies. While adversarial attack robustness has been extensively studied for image-based models, the susceptibility of VLMs to temporally-aware adversarial attacks against video in driving context poses a distinct and under examined threat. In this paper, we introduce novel adversarial attack against video targeting VLM models used for autonomous driving scenes named Spatial Temporal Coherence Adversarial Attack (STCA). Our attack comprise from three stages: modalities expansion, Spatial attack, and STCA attack. In modalities expansion, we propose caption-guided frame selection method in order to ensure that adversarial perturbation target the most semantically significant frames. Secondly.In spatial attack, we craft effective perturbation and preserve high similarity. Then the perturbed video generated fed into STCA stage that disrupt cross-frame temporal coherence using motion guided mask. Our method operate under black box threat model against victim target VLMs, relying solely on transferability from white-box surrogate model.We conduct our experiments on the BDD100K and nuScenes autonomous driving datasets across three VLM models: Video LLaVA-7B, Qwen2.5-VL-7B, and Dolphin. Experimental results demonstrate spatial attack achieves an ASR with high SSIM. Our finding reveal that existing video language model, remain highly susceptible to adversarial attack in autonomous driving scenarios, underscoring the urgent need for robust defense for VLM models.
Oct 5, 2026

TAPDreamer: Transferable Adversarial Patches for World Action Models

World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representations used across tasks and action policies. Existing attacks on these models optimize against the victim's actions or predicted futures and therefore require access to target-model outputs. In this paper, we propose an attack, TAPDreamer, against world action models that instead uses a public encoder alone to construct a fixed local perturbation that transfers across tasks and action architectures. TAPDreamer requires no target-policy queries. Our key insight is that interactions between patch-induced changes in attention weights and value vectors broadcast a nearly identical representation shift far beyond the patch footprint, and this shift remains stable across task observations. Guided by this insight, TAPDreamer uses six frames from one source task to maximize the global L1 distance between clean and patched encoder representations. In closed-loop evaluation, one frozen patch per benchmark, covering about 6.5% of the input, reduces FastWAM's success rate from 97.7% to 0.0% across 40 LIBERO tasks and from 90.86% to 0.0% across 50 RoboTwin tasks; matched random patches retain 81.5% and 79.2% success. The same patches reduce success to 1.45% and 1.00% on two DreamWAM configurations and to 10.60% on Motus. These results show that protecting downstream action generation alone is insufficient: defenses for world action models must also secure shared visual encoders against persistent local perturbations.
Oct 5, 2026

Reward Stealing Attack on Large Language Models

Adversarial attacks on Large Language Models (LLMs) aim to induce harmful content. However, existing methods suffer from high computational costs or strict model-pairing dependencies, limiting their scalability and transferability. We propose Reward Stealing Attack (ReSA), an adversarial attack framework that targets the latent safety reward underlying LLM alignment. ReSA employs maximum entropy inverse reinforcement learning to recover a proxy reward model solely from the aligned model's behavior. The extracted reward is then reversed at inference time to derive an adversarial policy, efficiently implemented via a reward-guided decoding mechanism. Experiments demonstrate that a single recovered reward generalizes across prompts and diverse models to reveal a fundamental alignment vulnerability, enabling ReSA to significantly outperform existing attacks in effectiveness and transferability. The code is available at https://github.com/GarminQ/ReSA.
Oct 5, 2026

Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning

Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This paper studies transfer-based black-box attacks on DRL: the attacker crafts observation perturbations on a white-box surrogate agent and feeds them to an unknown victim. We formulate the attack as return minimization under a per-step perturbation budget. We first show that transplanting transferable image-classification attacks (FGSM, MI-FGSM, and NI-FGSM) with a per-step objective yields perturbations that transfer but are no stronger than random noise of the same budget. We then propose a trajectory-level attack that optimizes a sequence of perturbations over a receding horizon through a differentiable model of the environment and a temperature-smoothed surrogate policy, with the same optimizers. On CartPole-v1 with ten DQN and DDQN agents and 100 surrogate--victim pairs, the trajectory-level attack outperforms per-step attacks and random noise in the white-box, cross-model, and cross-algorithm settings.
Oct 4, 2026

Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-source surrogate models are accessible. Existing targeted transfer attacks mainly align adversarial and target samples using global image-level features, such as encoder [CLS] embeddings. However, such coarse alignment insufficiently exploits patch-level visual structures, limiting transferability across heterogeneous closed-source MLLMs. We propose IAU-FOA, a visual-invariance-augmented feature optimal alignment attack with adaptive unbalanced transport, to improve targeted transferability against closed-source MLLMs. IAU-FOA aligns adversarial and target samples at both global and local levels: a cosine-based objective narrows their global semantic gap, while patch tokens are clustered into compact local patterns and matched through optimal transport for fine-grained feature alignment. Balanced optimal transport enforces fixed marginal masses even for local clusters without reliable counterparts, potentially introducing misleading alignment gradients. We therefore introduce confidence-adaptive unbalanced transport to relax these constraints for weakly matched clusters, aiming to reduce unreliable local alignment and improve adversarial transferability. We further study the effect of input transformations and propose visual-invariance augmentation, which applies bidirectional pixel-intensity rescaling and per-channel white-balance adjustment to simulate exposure, contrast, illumination, and color-temperature variations. This strategy encourages adversarial perturbations to generalize across different visual encoders. Extensive experiments on open-source and closed-source MLLMs show that IAU-FOA consistently outperforms state-of-the-art transferable attack methods. Code is available at https://github.com/jiaxiaojunQAQ/IAU-FOA.
Oct 3, 2026

Pareto-Improving Adversarial Attacks with Primal-Dual Regularization

Transferable adversarial attacks are arguably the most practical black-box threat model. Under the same perturbation budget, stronger transfer attacks attain higher attack success rate (ASR), yet their imperceptibility also tends to degrade. Under such a fixed-budget protocol, transferability and imperceptibility therefore appear to trade off against each other. We argue that this conflict is an artifact of fixed-budget evaluation, not an intrinsic trade-off. When attacks are compared on the ASR--imperceptibility Pareto frontier obtained by sweeping εε, stronger transfer attacks already attain better imperceptibility at matched ASR than weaker ones. To exploit this latent advantage, we introduce the stealthy transfer attack ST, a plug-in primal-dual wrapper that adds an L∞L_\infty saturation regularizer to the standard constrained objective and resolves it through a two-step primal-dual update: a projected primal step on the perturbation coupled with an L1L_1-ball projection on a dual variable that absorbs the regularizer through Fenchel duality, requiring no auxiliary models or handcrafted perceptual priors. Empirically, ST extends the Pareto frontier across different base attacks and additional surrogate architectures. At ε=16/255ε{=}16/255, average imperceptibility gains over each base attack are 17%17\% on LPIPS and 14%14\% on NIQE while ASR is preserved or improved. At matched high-ASR levels, the strongest ST variants further Pareto-dominate dedicated stealth-oriented transfer attacks, confirming that the latent imperceptibility advantage of strong transfer attacks can be unlocked by a primal-dual optimization wrapper without sacrificing transferability. Code will be made available at https://github.com/AndssY/ST.
Sep 30, 2026

Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework

A key bottleneck in adversarial transfer is a trajectory-level geometric disconnect: ambient gradients often drift away from the intrinsic data manifold, causing surrogate-specific overfitting. To rectify this, we propose Manifold Anchored Bilevel Transfer (MABT), a unified framework that anchors adversarial trajectories to the shared semantic subspace. MABT introduces a relaxed manifold-anchoring operator as a semantic rectifier to suppress off-manifold noise. With this constraint, we cast transfer attack generation as a distributional bilevel optimization problem that learns a geometry-aligned initialization by minimizing expected transfer risk under a surrogate uncertainty distribution. We further develop a Hessian-free solver with linear-time complexity to handle the resulting hierarchy. Experiments demonstrate improved transferability for 10 baseline attackers across 28 attack configurations, diverse victim architectures, and defense mechanisms.
Sep 29, 2026

FinRT: Distilling Adaptive Red-Teaming Strategies into Reusable Adversarial Generators in Consumer Finance

In regulated industries like consumer finance, seemingly harmless user queries can exploit large language model vulnerabilities, triggering safety failures and pushing responses dangerously close to policy limits. Existing automated red-teaming methods trade off attack effectiveness against generation cost, while treating coverage, severity, and diversity as incidental rather than joint objectives. We introduce FinRT, a structured framework that builds reusable adversarial prompt generators from adaptive red-teaming strategies. Across the six victim models in consumer finance, FinRT substantially outperforms adaptive search baselines while amortizing target-facing attack generation into a reusable generator. FinRT nearly doubles the attack success rate over the adaptive baseline Rainbow Teaming (32.9% vs. 17.2%), increases maximum adversarial severity by 33%, and preserves comparable intra-policy-domain semantic diversity to iterative search methods. Our method achieves high cross-model transferability while exhibiting distinct victim-family specialization patterns.
Sep 27, 2026

One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs

Adversarial attacks have long posed a fundamental threat to machine learning systems. As multimodal large language models (MLLMs) rapidly evolve and become widely deployed, assessing their vulnerability to such attacks is essential for their safe use. In this work, we investigate whether a single adversarial image can consistently mislead diverse frontier MLLMs in black-box settings. We propose O-Attack, a highly transferable black-box attack framework. This framework builds on our insight that surrogate models contain a broad, high-level, cross-modally aligned semantic space. This space extends beyond final-layer outputs and provides multiple semantically consistent representations that remain underexploited by existing attacks. Within this space, O-Attack anchors aligned representations, progressively broadens semantic conditions, and optimizes perturbations through semantic consensus to promote consistent target alignment. By fully exploiting this space with the same surrogate models as M-Attack, O-Attack raises attack success rates on GPT-5.4 (29.1% to 77.2%), Claude-4.6 (42.8% to 81.6%), and Gemini-3.1 (38.2% to 80.9%). Extensive experiments across 24 MLLMs show that O-Attack outperforms six state-of-the-art methods in black-box transferability, with consistent effectiveness across prompts and improved efficiency and imperceptibility. This work exposes the practical safety risks posed by black-box adversarial attacks against frontier MLLMs, underscoring the need for more rigorous robustness evaluation and more effective defenses.
Sep 26, 2026

AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion

Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with white-box access to one model to compromise independently deployed systems. This creates a shared vulnerability across models, yet existing defenses are not designed for this cross-model threat. We find that cross-model transfer aligns with shared internal representation geometry, making it a natural defense target. AnchorRep targets this geometry directly with a lightweight LoRA adapter that pushes the defended model's internal representations of harmful prompts away from those of a frozen anchor model on the same prompts. Training uses a small set of harmful prompts and no adversarial examples. Across five models and four architectural families, AnchorRep reduces cross-model attack success rate to <=1.1% on 2,000 transferred attacks (0% on two), including the largest drop on Mistral (36% -> 1.1%). Existing defenses can reduce transfer, but only at high cost either inducing up to 77% degenerate benign output or increasing over-refusal by up to 18%. Because such degenerate benign outputs are not captured by standard refusal-based metrics, we introduce the Benign Garble Rate to quantify them. Our results suggest that cross-model robustness can be achieved by shaping representation geometry, without requiring attack-specific training
Sep 22, 2026

Adversarial Attacks and Identity Leakage in De-Identification Systems: An Empirical Study

In this paper, we investigate the impact of adversarial attacks on identity encoders within a realistic de-identification framework. Our experiments show that the transferability of attacks transfers from an external surrogate model to the system model (e.g., CosFace to ArcFace) allows the adversary to cause identity information to leak in a sufficiently sensitive face recognition system. We present experimental evidence and propose strategies to mitigate this vulnerability. Specifically, we show how fine-tuning on adversarial examples helps to mitigate this effect for distortion-based attacks (i.e., snow, fog, etc.), while a simple low-pass filter can attenuate the effect of adversarial noise without affecting the de-identified images. Our mitigation results in a de-identification system that preserves its functionality while being significantly more robust to adversarial noise.
Sep 9, 2026

What Makes Adversarial Examples Transfer Across Deepfake Detectors?

Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibility shapes attack success remains poorly understood. Prior studies evaluate limited detector pools and rarely disentangle architectural from training factors. We conduct a controlled evaluation of adversarial transferability across 60 detectors spanning six backbones, two pretraining regimes, and five training-data configurations, using two attack procedures: AutoAttack (AA) and the Carlini--Wagner attack with Expectation over Transformation (CW--EOT). Matched comparisons reveal significantly higher transfer when source and target share an exact backbone, architecture family, pretraining regime, or training data. This compatibility structure is attack-dependent: exact backbone compatibility has the largest effect under AA, whereas shared pretraining and training data have the largest effects under CW--EOT. When transfer is averaged across non-target sources, mean attack success rate (ASR) is 7.21%7.21\% under AA and 19.52%19.52\% under CW--EOT. By contrast, a multi-source oracle combining both attacks attains a 64.48%64.48\% mean ASR after excluding exact backbone and training-data matches, showing that source averaging can substantially understate target vulnerability. We release 240,000 adversarially perturbed images, complete pairwise transfer results, detector configurations, and evaluation code. These findings establish source--target compatibility and source-model selection as central dimensions of credible transfer-based black-box robustness evaluation.
Aug 25, 2026

Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning

The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machine learning models. However, the involvement of a large number of users in FL also creates open opportunities for different adversaries, such as poisoning attacks, Byzantine attacks, and adversarial example attacks. Yet, recent research has disclosed that existing poisoning attacks and Byzantine attacks can not achieve satisfactory penetration in realistic FL scenarios caused by strong assumptions, e.g., client selection rate, and the ratio of malicious attackers. In this paper, the transferability of adversarial examples among different client models is analyzed to understand the relation between adversarial examples and clients' data distribution. Moreover, to mitigate the attacks of transferable adversarial examples, we design a defense mechanism stemming from the transferability of model robustness by adversarial training. As a result, through theoretical analysis of transferability, we gain insights into adversarial examples and the vulnerability of federated learning systems. Our proposed adversarial attack and defense methods are evaluated via real-life datasets in various settings to show their performance over the existing state-of-the-art methods.
Aug 23, 2026

Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key challenge is that safety behavior learned in the textual space does not reliably transfer to fused cross-modal representations, leaving multimodal inputs exploitable through latent semantic cues. We propose Text-Anchored Semantic Perturbation Attack (TA-SPA), a black-box jailbreak framework that optimizes transferable perturbations in a text-anchored semantic space. TA-SPA integrates Text-Anchored Semantic Factorization (TASF), which encourages the separation of cross-modal semantic factors from modality-specific residuals, with Semantic-Preserving Augmentation (SPA), which diversifies harmful target anchors while preserving semantic consistency. Experiments show strong attack effectiveness and transfer to commercial MLLMs, with competitive performance under representative defenses. Additional controls and probing support the intended factorization without implying perfect disentanglement, motivating representation-level safety alignment beyond input-level filtering.
Aug 15, 2026

Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples

Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transferability poses serious security threats to DNNs in practical applications. Input transformation techniques are widely used to enhance adversarial transferability by increasing the diversity of input images. However, existing methods primarily rely on local operations with limited degrees of freedom (DOF), such as block-wise shuffling and resizing, overlooking global perspective transformations that naturally arise from viewpoint changes. In this work, we propose a Perspective-Invariant Attack (PIA), which introduces a multi-DOF vertex sampling strategy that systematically covers the perspective transformation hierarchy from 2-DOF translation to 8-DOF projective mapping. By generating geometrically diverse input variations, PIA effectively reduces overfitting of adversarial perturbations to the surrogate model, thereby improving adversarial transferability. We further propose PIA-Mix, a generic extension that maintains a complementary transformation pool and efficiently combines our perspective transformation with auxiliary methods for improved transferability. Extensive experiments involving various DNN architectures, advanced defense mechanisms, and multimodal large language models (LLMs) demonstrate that PIA and PIA-Mix outperform state-of-the-art transfer-based attacks.
Aug 12, 2026

Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models. Beyond perturbation generation, transferability is fundamentally governed by the coupling of initialization, surrogate adaptation, and gradient dynamics. We revisit this challenge from a bilevel-minimax perspective and propose BMAT (Bilevel-Minimax Adversarial Transfer). The bilevel formulation captures the dependency between initialization and perturbation, while the inner minimax problem promotes surrogate robustness for cross-architecture generalization. Algorithmically, we develop an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization. We further provide theoretical insights into the optimization dynamics of the proposed bilevel-minimax framework. Extensive experiments on classification and segmentation benchmarks show that BMAT outperforms more than 10 strong baselines across more than 30 victim models, improving both intra- and cross-architecture transfer and yielding up to a 2x reduction in mIoU. Code is available at https://github.com/callous-youth/BMAT.
Aug 9, 2026

IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack

Unrestricted adversarial transfer attacks are important for evaluating the black-box robustness of deep visual models. Diffusion-based attacks have shown promising transferability and visual imperceptibility by optimizing adversarial perturbations along denoising trajectories in latent space. However, existing methods are limited by two challenges: memory-intensive multistep backpropagation and frequency-agnostic perturbation over intermediate latents. To address these issues, we propose IDATA, a memory-efficient diffusion framework for unrestricted adversarial transfer attack. IDATA consists of two key components: an Invertible Diffusion Module (IDM) and a Low-Frequency Constraint Module (LFCM). Specifically, IDM reformulates adversarial optimization over diffusion trajectories as an invertible process, enabling constant-memory backpropagation through on-demand reconstruction of intermediate states instead of storing the full denoising chain. Moreover, LFCM leverages Discrete Wavelet Transform (DWT) to decompose latent variables into low- and high-frequency components, restricting perturbations to semantically stable low-frequency subspaces, thereby improving transferability while preserving visual imperceptibility. Extensive experiments on multiple benchmarks and diverse model architectures demonstrate that IDATA consistently outperforms state-of-the-art baselines in attack success rate, memory efficiency, and visual imperceptibility. These results suggest that IDATA is a promising tool for black-box robustness evaluation of deep visual models. Code is available at https://github.com/colourful-pan/IDATA.
Aug 7, 2026

Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits

Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood. In this work, we investigate DLLMs both as targets and as adversaries, exposing mechanistic vulnerabilities in diffusion-based alignment. We first show that safety alignment in DLLMs remains sparse and transferable across architectures. DLLMs initialized from autoregressive predecessors inherit the same mechanistic safety footprint as their source models, enabling transfer attacks via direct safety neuron mapping and pruning. Self-pruning increases attack success rates (ASR) from 2.6% to 73.8% on LLaDA and from 1.9% to 86.6% on Dream, while transfer pruning from Qwen2.5 increases ASR from 1.9% to 73.2% on Dream and from 7.0% to 86.3% on Fast-dLLM. Building on these findings, we introduce SN-Guided Diffusion, a fully offline black-box jailbreak framework that steers the diffusion process away from safety-triggering regions using a weighted safety neuron loss, which achieves near-perfect prompt separability (AUROC = 1.0 for benign-vs-jailbreak discrimination). Across multiple open and proprietary targets, our method achieves a transfer ASR of up to 77.1% on Llama-3-8B-Instruct, 86.9% on Qwen2.5-7B-Instruct, and 74.3% against Gemini-2.5-Flash-Lite, while requiring only 20 generation episodes per prompt. Compared to prior jailbreaking frameworks, our method achieves competitive transferability with orders-of-magnitude lower generation cost. Our codebase is available at https://github.com/ellyoana/sn-guided-diffusion.
Aug 5, 2026

Season: Spectrum-Aware Orthogonal Gradient Refinement for Transfer-Based Adversarial Attacks

Transfer-based adversarial attacks often transfer poorly across heterogeneous architectures because CNNs favor local textures while Vision Transformers (ViTs) rely on global shapes. We propose Season, a spectrum-aware orthogonal gradient refinement framework for L-infinity transfer attacks against black-box target models on ImageNet, using a white-box surrogate. Season decomposes each update into a low-frequency branch capturing structural cues and a high-frequency branch capturing textures. A low-saliency guidance scheme reallocates high-frequency energy to background regions, preserving foreground structures that ViTs depend on. An orthogonal projection then forces the textural update to lie in the orthogonal complement of the structural direction, mitigating feature interference. As a training-free plug-and-play wrapper, Season enhances eight gradient-stabilization and input-enhancement attacks without modifying their cores. Across eight CNN, ViT, and MLP targets, Season improves transfer success rate by 6.6 percentage points on average and up to 16.0 points over strong baselines under a unified protocol.
Aug 2, 2026

Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems

Text-to-image (T2I) systems typically have prompt-level safety filters before the generator to block unsafe requests, yet such systems remain vulnerable to malicious jailbreak prompts. Transfer-based attacks construct adversarial prompts offline without querying the target, but they tend to overfit to a single surrogate. Moreover, they explore a large search space in which semantic or perceptual similarity alone cannot guarantee both filter evasion and preservation of the unsafe generation intent, wasting effort on low-potential candidates. We observe that the filter and the generator process the same prompt under different objectives and representations, and term this gap the Filter-Generator Discrepancy (FGD), which allows a perturbation to reduce a prompt's perceived risk to the filter while preserving the visual concept needed by the generator. Building on FGD, we propose a zero-query jailbreak framework that screens perturbations into a high-potential candidate set via observable discrepancy rules at the tokenization and semantic stages, and then performs a surrogate-ensemble evolutionary search that requires no access to the target. Experiments on six black-box pipelines and a commercial online service show that our method consistently outperforms representative baselines, raising the average attack success rate to 29.2% (MHSC) and 33.3% (Q16) across the six pipelines and improving over the strongest baseline by about 8 and 12 percentage points, respectively.
Jul 31, 2026

DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models

Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boundaries of deep face recognition (FR) systems are often sufficiently narrow that they can be conflated, rendering the models vulnerable to adversarial attacks. In such scenarios, the FR system fails to distinguish between an authentic source and a meticulously crafted adversarial face. Existing adversarial methods targeting facial biometrics are limited in both performance and their ability to generate high-quality images that are imperceptible to humans. Moreover, these methods often fail when the source and target images belong to different demographic groups or genders. To address these limitations, we present a novel approach for adversarial face generation via latent-space optimization. We leverage latent diffusion models directly to guide generation toward target identity embeddings, as measured by a face recognition model. Our proposed DiffAttack framework has been evaluated on standard benchmarks, such as the FFHQ and CelebA-HQ datasets. DiffAttack significantly outperforms existing adversarial techniques, achieving a high average attack success rate of 84.86% across multiple face recognition models (e.g., FaceNet). Notably, DiffAttack demonstrates superior transferability, surpassing traditional noise-based methods by over 15.28% and semantic-based approaches by approximately 5.21% on benchmark datasets like FFHQ and CelebA-HQ.