相关论文: Vaccine: Perturbation-aware Alignment for Large La…

Recent works have shown that powerful pre-trained language models (PLM) can be fooled by small perturbations or intentional attacks. To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs.…

With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the safety of this fine-tuning process more important than ever.…

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection, where malicious commands embedded in untrusted data…

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the…

While Large Language Models (LLMs) have achieved remarkable progress, they remain vulnerable to jailbreak attacks. Existing methods, primarily relying on discrete input optimization (e.g., GCG), often suffer from high computational costs…

The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform basic security scans, they often fail to detect subtle…

Vision-Language-Action (VLA) models have become foundational to modern embodied AI systems. By integrating visual perception, language understanding, and action planning, they enable general-purpose task execution across diverse…

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning…

Conventional Data Leakage Prevention (DLP) systems suffer from the following major drawback: Privacy policies that define what constitutes data leakage cannot be seamlessly defined and enforced across heterogeneous forms of communication.…

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…

As Vision-Language Models (VLMs) demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models (LLMs),…

Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and…

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…

Large language models (LLMs) reproduce misinformation not by memorizing false facts alone, but by learning the linguistic patterns that make falsehoods persuasive, such as hedging, false presuppositions, and fabricated citations. We propose…

Language model finetuning often results in learning undesirable traits in combination with desired ones. To address this, we propose inoculation prompting: modifying finetuning data by prepending a short system-prompt instruction that…