The paper introduces Learning to Detect (LoD), a framework for identifying unseen jailbreak attacks in Large Vision‑Language Models without relying on attack data or hand‑crafted heuristics. LoD extracts layer‑wise safety representations via Multi‑modal Safety Concept Activation Vectors and compresses them into a one‑dimensional anomaly score using a Safety Pattern Auto‑Encoder. Experiments show that LoD achieves state‑of‑the‑art AUROC across diverse unseen attacks on multiple LVLMs while improving efficiency.
arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic...
arXiv:2602. 18154v2 Announce Type: replace-cross Abstract: Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs).
arXiv:2602. 12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety.
The paper introduces TA-SPA, a black‑box jailbreak method for multimodal large language models that generates transferable perturbations in a text‑anchored semantic space. It combines Text‑Anchored Semantic Factorization (TASF) to separate cross‑modal semantic factors from modality‑specific residuals with Semantic‑Preserving Augmentation (SPA) to diversify harmful target anchors while maintaining semantic consistency. Experiments demonstrate strong attack effectiveness and transferability to commercial MLLMs, with competitive performance against representative defenses.
arXiv:2606. 03647v1 Announce Type: cross Abstract: Accurately evaluating adversarial robustness is a longstanding challenge.
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 s...
arXiv:2607. 22716v1 Announce Type: cross Abstract: In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations.
arXiv:2509. 03985v2 Announce Type: replace-cross Abstract: In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs.
arXiv:2606. 16751v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks.
arXiv:2607. 19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates.
arXiv:2606. 07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge.
arXiv:2606. 24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs).