Related papers: Safety Layers in Aligned Large Language Models: Th…

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts…

Fine-tuning-as-a-Service introduces a critical vulnerability where a few malicious examples mixed into the user's fine-tuning dataset can compromise the safety alignment of Large Language Models (LLMs). While a recognized paradigm frames…

Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…

The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation…

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…

Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

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…

Log Anomaly Detection (LAD) seeks to identify atypical patterns in log data that are crucial to assessing the security and condition of systems. Although Large Language Models (LLMs) have shown tremendous success in various fields, the use…

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,…

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…

Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted significant security vulnerabilities in fine-tuned LLMs. Existing…

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the…

Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…

Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM). However, security in open federated…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, finetuning-based ones that compromise LLMs' safety alignment…

The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on parameters, gradients, or internal representations, we observe that they can be effectively…