Related papers: Harnessing Hyperbolic Geometry for Harmful Prompt …

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…

Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque and poorly controlled. In this work, we present a…

We present LatentBiopsy, a training-free method for detecting harmful prompts by analysing the geometry of residual-stream activations in large language models. Given 200 safe normative prompts, LatentBiopsy computes the leading principal…

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the…

Video Large Language Models (VideoLLMs) have emerged as powerful tools for understanding videos, supporting tasks such as summarization, captioning, and question answering. Their performance has been driven by advances in frame sampling,…

Large Language Models (LLMs) are increasingly deployed via third-party system prompts downloaded from public marketplaces. We identify a critical supply-chain vulnerability: conditional system prompt poisoning, where an adversary injects a…

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution (RCE) risks during model loading. Recent defenses, such as…

With the rapid development of text-to-image generation technology, accurately assessing the alignment between generated images and text prompts has become a critical challenge. Existing methods rely on Euclidean space metrics, neglecting…

Text-image alignment constitutes a foundational challenge in multimedia content understanding, where effective modeling of cross-modal semantic correspondences critically enhances retrieval system performance through joint embedding space…

Large Language Models (LLMs) have gained considerable popularity and protected by increasingly sophisticated safety mechanisms. However, jailbreak attacks continue to pose a critical security threat by inducing models to generate…

Recent advances in Large Vision-Language Models (LVLMs) have showcased strong reasoning abilities across multiple modalities, achieving significant breakthroughs in various real-world applications. Despite this great success, the safety…

Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…

Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities. As they find increased use in sensitive tasks, safety concerns have gained…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Pre-trained Language Models (PLMs) may be poisonous with backdoors or bias injected by the suspicious attacker during the fine-tuning process. A core challenge of purifying potentially poisonous PLMs is precisely finding poisonous…

Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose significant security threats. Some defenses have been proposed…

Prompting has emerged as a practical way to adapt frozen vision-language models (VLMs) for video anomaly detection (VAD). Yet, existing prompts are often overly abstract, overlooking the fine-grained human-object interactions or action…