Related papers: Compiling Activation Steering into Weights via Nul…
Safety-aligned large language models (LLMs) remain vulnerable to backdoor attacks. Recent model editing-based approaches enable efficient backdoor injection by directly modifying a small set of parameters to map triggers to attacker-desired…
Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…
Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…
Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…
Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While it assumes semantic equivalence between the original and compiled graphs, we first…
The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…
Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…
The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…
Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…
Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…
Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…
Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…
Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…
With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…
The integration of large language models (LLMs) into robotic control pipelines enables natural language interfaces that translate user prompts into executable commands. However, this digital-to-physical interface introduces a critical and…
Safety alignment mechanisms in Large Language Models (LLMs) often operate as latent internal states, obscuring the model's inherent capabilities. Building on this observation, we model the safety mechanism as an unobserved confounder from a…