Home Knowledge Base Adversarial Attack

Adversarial Attack

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition

arXiv:2606.05678v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems have become widely used for multilingual speech-to-text transcription. Their robustness to adversarial attacks has become an important topic for the community. Existing adversarial attacks directly add adversarial noise to the speech audio.

arXiv CS 5d ago

Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks

arXiv:2605.31219v1 Announce Type: new Abstract: While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wise attacks frequently introduce unnatural, high-frequency visual artifacts, while latent-space frameworks are confined by the limited search space of low-dimensional manifolds and inherent reconstruction flaws. To resolve these limitations, we propose Latent Geometric Chords (LGC) for...

arXiv CS 9d ago

GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks

arXiv:2606.01560v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges in assortative graphs and assortative edges in disassortative graphs. This structural inversion creates structure-feature mismatches that disrupt neighborhood aggregation across different graph types.

arXiv CS 8d ago

Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation

arXiv:2606.01892v1 Announce Type: new Abstract: Robot localization systems are critical for autonomous navigation and safety. Adversarial perturbations can mislead these systems, resulting in mislocalization, navigation errors, or unsafe interactions, especially in mission-critical scenarios. This paper investigates the vulnerability of deep learning based localization pipelines to adversarial attacks.

arXiv CS 8d ago

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

arXiv:2603.24511v2 Announce Type: replace Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations. We deploy frontier agents, such as Claude Code and Codex, in an autoresearch loop with access to a library of 30+ prior methods and an evaluation script with a fixed compute budget. We show this pipeline to be effective in jailbreaking OpenAI's...

arXiv CS 8d ago

Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models

Announce Type: new Abstract: Vision-Language Models (VLMs), such as CLIP, have shown strong zero-shot generalization but remain highly vulnerable to adversarial perturbations, posing serious risks in real-world applications. Test-time defenses for VLMs have recently emerged as a promising and efficient approach to defend against adversarial attacks without requiring costly large-scale retraining. In this work, we uncover a surprising phenomenon: under diverse input transformations,...

arXiv CS 5d ago

Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics

arXiv:2606.03556v1 Announce Type: new Abstract: Vision-language-action (VLA) models are gaining attention in robotics, yet their robustness to adversarial attacks remains largely unexplored. Existing work shows that adversarial patches can mislead VLA-based robots but assumes full access to the entire execution trajectory, an unrealistic requirement in practice. We address this limitation by formulating a partially observable threat model, where the adversary can exploit only a short prefix...

arXiv CS 7d ago

Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

arXiv:2606.06833v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription decisions are inherently made on incomplete information. This causal constraint serves as an information bottleneck on attackers, significantly limiting attack performance. Our new Semantic Gambit attack breaks this causal limitation by augmenting the adversary with predictive context...

arXiv CS 2d ago

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

arXiv:2605.12813v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs. We formulate hallucination elicitation as a constrained optimization problem, where the goal is to find semantically coherent adversarial prompts that are equivalent to benign user prompts. Existing attack methods remain...

arXiv CS 8d ago

Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation

arXiv:2606.09536v1 Announce Type: new Abstract: Conventional one-hot encodings often yield poorly calibrated models, being overconfident under attack, and letting entropy-based detection algorithms fail. Previous image classification works have demonstrated that Hadamard-coded output representations can improve adversarial robustness. However, attempts to integrate Hadamard codes into semantic segmentation fall far behind state-of-the-art models in mean intersection-over-union performance.

arXiv CS 1d ago