相关论文: Gradient Co-occurrence Analysis for Detecting Unsa…

Large Language Models (LLMs) are implicit troublemakers. While they provide valuable insights and assist in problem-solving, they can also potentially serve as a resource for malicious activities. Implementing safety alignment could…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

Multimodal Large Language Models (MLLMs) are susceptible to the implicit reasoning risk, wherein innocuous unimodal inputs synergistically assemble into risky multimodal data that produce harmful outputs. We attribute this vulnerability to…

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…

Text-to-Image (T2I) models have made remarkable progress in generating images from text prompts, but their output quality and safety still depend heavily on how prompts are phrased. Existing safety methods typically refine prompts using…

System prompts provide a lightweight yet powerful mechanism for conditioning large language models (LLMs) at inference time. While prior work has focused on English-only settings, real-world deployments benefit from having a single prompt…

As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability…

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to…

Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper,…

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning and text generation. However, these models can inadvertently generate unsafe or biased responses when prompted with problematic inputs, raising…

As large language models (LLMs) are increasingly integrated into numerous applications across various domains, LLMs' safety becomes a critical concern for both application developers and intended users. Currently, great efforts have been…

Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious…

Detecting prompt injection and jailbreak attacks is critical for deploying LLM-based agents safely. As agents increasingly process untrusted data from emails, documents, tool outputs, and external APIs, robust attack detection becomes…

Despite tremendous success of modern neural networks, they are known to be overconfident even when the model encounters inputs with unfamiliar conditions. Detecting such inputs is vital to preventing models from making naive predictions…

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning…