Related papers: SEA: Low-Resource Safety Alignment for Multimodal …

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual inputs, yet modality alignment remains one of the most challenging aspects. Current MLLMs typically rely on simple adapter…

Safeguard models help large language models (LLMs) detect and block harmful content, but most evaluations remain English-centric and overlook linguistic and cultural diversity. Existing multilingual safety benchmarks often rely on…

Fine-tuning on task-specific data to boost downstream performance is a crucial step for leveraging Large Language Models (LLMs). However, previous studies have demonstrated that fine-tuning the models on several adversarial samples or even…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks and complex risk combinations. In this paper, we begin with…

Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Understanding LLMs' knowledge deficiencies by exhaustively…

The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstream variants, enabling transferable attacks across…

As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to…

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly…

Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many companies provide fine-tuning API services, enabling users to…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Multimodal Large Language Models (MLLMs) are rapidly evolving, demonstrating impressive capabilities as multimodal assistants that interact with both humans and their environments. However, this increased sophistication introduces…

Safety alignment -- training large language models (LLMs) to refuse harmful requests while remaining helpful -- is critical for responsible deployment. Prior work established that safety behaviors are governed by low-rank structures,…

Safety alignment is critical for LLM-powered systems. While recent LLM-powered guardrail approaches such as LlamaGuard achieve high detection accuracy of unsafe inputs written in English (e.g., ``How to create a bomb?''), they struggle with…

Safety concerns of Multimodal large language models (MLLMs) have gradually become an important problem in various applications. Surprisingly, previous works indicate a counterintuitive phenomenon that using textual unlearning to align MLLMs…

The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities. Meanwhile, existing safety alignment methods…

Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing serious privacy risks. To mitigate this, MLLM unlearning methods are proposed, which fine-tune MLLMs to reduce…

With the growing deployment of Vision-Language Models (VLMs) in real-world applications, previously overlooked safety risks are becoming increasingly evident. In particular, seemingly innocuous multimodal inputs can combine to reveal…

Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we…