Attention-Based Adversarial Attacks

Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate because financial tabular data involve domain-specific constraints, severe class imbalance, and asymmetric attacker capability. We argue that, in this setting, robustness is not only an attribute of the model, but also an attribute of the evaluation protocol. Different ways of enforcing constraints and capability can lead to substantially different robustness conclusions. This paper presents FraudBench, a protocol-sensitive benchmark for adversarial robustness evaluation in financial fraud and credit-risk detection. Rather than treating domain constraints as post-hoc validity checks, FraudBench evaluates the same dataset--model--attack--defence setting under three matched protocols: unconstrained attacks, post-hoc feasibility filtering, and deployment-aware constraint-integrated attacks. FraudBench covers four public financial datasets, and evaluates neural, tree-based, and ensemble models using three attack settings. Our results show that robustness conclusions are highly protocol-sensitive. On Lending Club Loan Data under the white-box setting, post-hoc filtering leaves only 3.7 feasible-flipped examples on average, whereas in-attack projection with attacker mutability masking produces 2,832.3 feasible-flipped examples under the same perturbation budget. The results on IEEE-CIS further show that feasibility and attacker capability are separate axes, while black-box evaluation shows that protocol choice can alter model-family rankings. These findings suggest that fraud robustness evaluation should report predictive degradation and attack feasibility jointly, and should incorporate domain constraints into attack generation rather than treating them as post-processing checks.

Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical systems. Detection transformers have emerged as leading object detectors, yet their adversarial robustness remains comparatively underexplored. Most existing attacks target the detection output rather than the attention mechanism that makes these models distinctive. In this paper, we introduce the first attack that directly optimizes an encoder-attention objective under an imperceptible, bounded $\ell_\infty$ perturbation. Rather than introducing an attacker-owned sink token through a visible patch, it drives the model's own attention toward a corrupted target. We argue that encoder attention concentrates the model's spatial reasoning, so corrupting it propagates through the detection pipeline more disruptively than perturbing the detection output alone. Our attack reduces DETR-R50 mAP on COCO from 42.1 to 0.97, a $\sim 4\times$ reduction in resulting mAP over the strongest existing attack under an identical perturbation budget and iteration count. We further show that this vulnerability is not specific to a particular corruption objective: across four qualitatively distinct targets, dispersion, re-ranking, permutation, and peak-suppression, detection consistently drops below 3 mAP, suggesting that the weakness arises from disrupting the attention structure itself rather than from any single target. Finally, we demonstrate that the attack generalizes across attention formulations, reducing DINO-Swin-L from 56.8 to 1.44 mAP against 7.3 for the strongest prior attack, establishing state-of-the-art on both dense and deformable attention.

The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models. Although substantial progress has been made in detecting AI-generated videos, proactive defenses against I2V models remain underexplored. In particular, current proactive defenses against I2V models predominantly rely on gradient-based adversarial attacks, which require defenders to possess GPUs with substantial memory resources (VRAM) to generate adversarial examples. To address this issue, we propose I2VShield, a privacy protection method based on generative adversarial attacks tailored to Diffusion Transformer (DiT)-based I2V models. The proposed method primarily consists of two components: (1) a text-adaptive perturbation generation framework integrating adversarial learning to mitigate computational overhead while maintaining visual imperceptibility; and (2) an untargeted Multimodal Attention Disruption (MAD) attack that exploits the inherent vulnerabilities of DiT-based I2V models, maximizing the deviation of the internal attention features from their clean states. Extensive experiments demonstrate that our approach achieves highly competitive protection performance across various datasets and mainstream DiT-based I2V models, particularly in disrupting spatiotemporal coherence, while substantially reducing computational costs.

Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.g., adversarial patches, while recent test-time defenses mitigate them by suppressing image tokens with abnormally high attention scores. These defenses exploit a strong coupling between attention and adversarial effectiveness: adversarial tokens often need to attract substantial attention to influence the prediction. We introduce adversarial decoys, independently optimized image patches that redirect the attention, and therefore related defenses, toward selected target tokens. Rather than jointly optimizing misclassifications and defense evasion, our approach decouples the two objectives: the original adversarial region induces the incorrect prediction, while a separate decoy manipulates the attention ranking used by the defense. A layer-wise objective increases target-token attention and promotes these tokens above competing non-target ones. Since the decoy is optimized independently of the underlying attack, the method is attack-agnostic and can be easily integrated with any existing adversarial patch attack. Experiments on ImageNet across multiple ViT architectures and attacks show that decoys can redirect high attention scores away from the true adversarial region while preserving much of the attack effectiveness. These results reveal a fundamental limitation of using attention magnitude as an indicator of adversarial relevance.

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries. This paper studies cross-query response manipulation, where a single adversarial example is expected to remain effective across diverse user queries. We first analyze the limitations of existing attacks and find that successful transfer is closely associated with preserving an image-dominant attention pattern during response generation. Motivated by the observation, we propose Attention Hijacking, a novel adversarial attack that explicitly steers internal attention distributions toward a persistent image-dominant pattern. By amplifying the influence of visual tokens on target response tokens while suppressing the competing influence of textual tokens, our method reduces the dependence of the manipulated output on the specific wording of the query. Extensive experiments on widely used VLMs show that Attention Hijacking substantially improves cross-query transferability across diverse target responses and unseen queries. The method also extends effectively to multiple attack scenarios, offering new insights into the role of attention stability in transferable response manipulation for VLMs.

Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understood. We introduce the Attention Redistribution Attack (ARA), a white-box adversarial attack that identifies safety-critical attention heads and crafts nonsemantic adversarial tokens that redirect attention away from safety-relevant positions. Unlike prior jailbreak methods operating at the semantic or output-logit level, ARA targets the geometry of softmax attention on the probability simplex using Gumbel-softmax optimization over targeted heads. Across LLaMA-3-8B-Instruct, Mistral-7B-Instruct-v0.1, and Gemma-2-9B-it, ARA bypasses safety alignment with as few as 5 tokens and 500 optimization steps, achieving 36% ASR on Mistral-7B and 30% on LLaMA-3 against 200 HarmBench prompts, while Gemma-2 remains at 1%. Our principal mechanistic finding is a dissociation between ablation and redistribution: zeroing out the top-ranked safety heads produces at most 1 flip among 39 to 50 baseline refusals, while ARA targeting the corresponding safety-heavy layers flips 72/200 prompts on Mistral-7B and 60/200 on LLaMA-3. This suggests that safety is not localized in these heads as removable components, but emerges from the attention routing they perform. Removing a head allows compensation through the residual stream, while redirecting its attention propagates a corrupted signal downstream.

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer from slow convergence due to gradient conflict between adversarial objectives and the model's safety-retrieval mechanism. We propose Attention-Guided Visual Jailbreaking, which circumvents rather than overpowers safety alignment by directly manipulating attention patterns. Our method introduces two simple auxiliary objectives: (1) suppressing attention to alignment-relevant prefix tokens and (2) anchoring generation on adversarial image features. This simple yet effective push-pull formulation reduces gradient conflict by 45% and achieves 94.4% attack success rate on Qwen-VL (vs. 68.8% baseline) with 40% fewer iterations. At tighter perturbation budgets ($ε=8/255$), we maintain 59.0% ASR compared to 45.7% for standard methods. Mechanistic analysis reveals a failure mode we term safety blindness: successful attacks suppress system-prompt attention by 80%, causing models to generate harmful content not by overriding safety rules, but by failing to retrieve them.

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g., CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: Local Attention Refinement Module and Global Attention Constraint Module. Our goal is to maintain the generalization of the CLIP model and enhance its adversarial robustness. Additionally, the Global Attention Constraint Module acquires text-guided attention from both the target and original models using clean examples. Its objective is to maintain model performance on clean samples while enhancing overall robustness. However, we observe that the method occasionally focuses on irrelevant or spurious features, which can lead to suboptimal performance and undermine its robustness in certain scenarios. To overcome this limitation, we further propose a novel approach called Complementary Text-Guided Attention (Comp-TGA). This method integrates two types of foreground attention: attention guided by the class prompt and reversed attention driven by the non-class prompt. These complementary attention mechanisms allow the model to capture a more comprehensive and accurate representation of the foreground. The experiments validate that TGA-ZSR and Comp-TGA yield 9.58% and 11.95% improvements respectively, in zero-shot robust accuracy over the current state-of-the-art techniques across 16 datasets.

Currently, open-sourced large language models (OSLLMs) have demonstrated remarkable generative performance. However, as their structure and weights are made public, they are exposed to jailbreak attacks even after alignment. Existing attacks operate primarily at shallow levels, such as the prompt or embedding level, and often fail to expose vulnerabilities rooted in deeper model components, which creates a false sense of security for successful defense. In this paper, we propose Safety Attention Head Attack (SAHA), an attention-head-level jailbreak framework that explores the vulnerability in deeper but insufficiently aligned attention heads. SAHA contains two novel designs. Firstly, we reveal that deeper attention layers introduce more vulnerability against jailbreak attacks. Based on this finding, SAHA introduces Ablation-Impact Ranking head selection strategy to effectively locate the most vital layer for unsafe output. Secondly, we introduce a boundary-aware perturbation method, i.e. Layer-Wise Perturbation, to probe the generation of unsafe content with minimal perturbation to the attention. This constrained perturbation guarantees higher semantic relevance with the target intent while ensuring evasion. Extensive experiments show the superiority of our method: SAHA improves ASR by 14% over SOTA baselines, revealing the vulnerability of the attack surface on the attention head. Our code is available at https://anonymous.4open.science/r/SAHA.

Extensive research demonstrates that Deep Reinforcement Learning (DRL) models are susceptible to adversarially constructed inputs (i.e., adversarial examples), which can mislead the agent to take suboptimal or unsafe actions. Recent methods improve attack effectiveness by leveraging future rewards to guide adversarial perturbation generation over sequential time steps (i.e., reward-based attacks). However, these methods are unable to capture dependencies between different time steps in the perturbation generation process, resulting in a weak temporal correlation between the current perturbation and previous perturbations.In this paper, we propose a novel method called Advantage-based Adversarial Transformer (AAT), which can generate adversarial examples with stronger temporal correlations (i.e., time-correlated adversarial examples) to improve the attack performance. AAT employs a multi-scale causal self-attention (MSCSA) mechanism to dynamically capture dependencies between historical information from different time periods and the current state, thus enhancing the correlation between the current perturbation and the previous perturbation. Moreover, AAT introduces a weighted advantage mechanism, which quantifies the effectiveness of a perturbation in a given state and guides the generation process toward high-performance adversarial examples by sampling high-advantage regions. Extensive experiments demonstrate that the performance of AAT matches or surpasses mainstream adversarial attack baselines on Atari, DeepMind Control Suite and Google football tasks.

Large Vision-Language Models (LVLMs) are foundational to modern multimodal applications, yet their susceptibility to adversarial attacks remains a critical concern. Prior white-box attacks rarely generalize across tasks, and black-box methods depend on expensive transfer, which limits efficiency. The vision encoder, standardized and often shared across LVLMs, provides a stable gray-box pivot with strong cross-model transfer. Building on this premise, we introduce PA-Attack (Prototype-Anchored Attentive Attack). PA-Attack begins with a prototype-anchored guidance that provides a stable attack direction towards a general and dissimilar prototype, tackling the attribute-restricted issue and limited task generalization of vanilla attacks. Building on this, we propose a two-stage attention enhancement mechanism: (i) leverage token-level attention scores to concentrate perturbations on critical visual tokens, and (ii) adaptively recalibrate attention weights to track the evolving attention during the adversarial process. Extensive experiments across diverse downstream tasks and LVLM architectures show that PA-Attack achieves an average 75.1% score reduction rate (SRR), demonstrating strong attack effectiveness, efficiency, and task generalization in LVLMs. Code is available at https://github.com/hefeimei06/PA-Attack.

Targeted adversarial attacks on Large Vision-Language Models (LVLMs) test whether small image perturbations can steer model responses toward attacker-specified content. Under the standard L-infinity constraint, targeted attacks become a regional perturbation budget allocation problem: attack success depends not only on the perturbation objective, but also on which regions receive updates and in what order. Existing localized attacks improve over global perturbations but rely on stochastic spatial sampling, often updating weakly influential regions. We address this limitation through an attention-based analysis showing that cross-modal attention identifies adversarially sensitive regions and that perturbing high-attention hotspots induces predictable redistribution toward subsequent salient regions. These findings motivate attention-guided region sequencing, which begins from dominant hotspots and progressively moves the update support toward next-salient regions. Based on these principles, we propose Stage-wise Attention-Guided Attack (SAGA), a black-box region-sequencing framework that uses a fixed attention map from an open-source LVLM to guide perturbation updates without accessing target-model parameters, gradients, or attention maps. Across ten closed-source and open-source LVLMs, SAGA achieves state-of-the-art attack success rates and the best overall imperceptibility. The source code is available at https://github.com/jaehyun-kwak/SAGA.