相关论文: Safeguarding Vision-Language Models: Mitigating Vu…

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and…

Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and…

Advancements in Large Vision-Language Models (LVLMs) have demonstrated promising performance in a variety of vision-language tasks involving image-conditioned free-form text generation. However, growing concerns about hallucinations in…

Large vision-language models (LVMs) extend large language models (LLMs) with visual perception capabilities, enabling them to process and interpret visual information. A major challenge compromising their reliability is object hallucination…

Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its adversarial robustness remains unexplored. We show that existing encoder-based attacks cannot fully…

Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulnerabilities. Large Language Models (LLMs) have shown…

Diffusion models have achieved impressive success in generating photorealistic images, but challenges remain in ensuring precise semantic alignment with input prompts. Optimizing the initial noisy latent offers a more efficient alternative…

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed…

Recent advances in reinforcement learning (RL) have strengthened the reasoning capabilities of vision-language models (VLMs). However, enhancing policy exploration to better scale test-time compute remains largely underexplored. In…

Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue. These improvements are evident in a wide…

Large Vision-Language Models (LVLMs) are increasingly equipped with robust safety safeguards to prevent responses to harmful or disallowed prompts. However, these defenses often focus on analyzing explicit textual inputs or relevant visual…

To leverage the full potential of Large Language Models (LLMs) it is crucial to have some information on their answers' uncertainty. This means that the model has to be able to quantify how certain it is in the correctness of a given…

Vision-Language Models (VLMs) have demonstrated immense capabilities in multi-modal understanding and inference tasks such as Visual Question Answering (VQA), which requires models to infer outputs based on visual and textual context…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…

Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power autonomous agents. Prior work typically focus on maximizing attack success rate (ASR) but…

Vision-language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over inter-object interactions. We study the impact of visual perturbations, specifically…

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

With the increasing capabilities of large language models (LLMs), these high-performance models have achieved state-of-the-art results on a wide range of natural language processing (NLP) tasks. However, the models' performance on…

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete…

Large language models (LLMs) have recently shown strong potential in vulnerability detection (VD). However, accurately detecting vulnerabilities in real-world repositories requires reasoning over complex contextual interactions. Existing…