相关论文: Soft Token Attacks Cannot Reliably Audit Unlearnin…
System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…
Large language models (LLMs) have achieved remarkable success across natural language processing tasks, yet their widespread deployment raises pressing concerns around privacy, copyright, security, and bias. Machine unlearning has emerged…
Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…
Large Language Models (LLMs), pre-trained on massive text corpora, exhibit remarkable human-level language understanding, reasoning, and decision-making abilities. However, they tend to memorize unwanted information, such as private or…
Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. Data owners may request the removal of their data from a trained model due to privacy or copyright concerns. However, exactly…
An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or copyrighted information. In recent years, unlearning has…
LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain…
Unlearning in Large Language Models (LLMs) is essential for ensuring ethical and responsible AI use, especially in addressing privacy leak, bias, safety, and evolving regulations. Existing approaches to LLM unlearning often rely on retain…
Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In a potential real-world scenario,…
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…
Large language models (LLMs) increasingly operate on long inputs, yet their behavior when harmful sentences are sparsely embedded within such inputs remains poorly understood. We present a sensitivity analysis that probes how LLMs extract…
Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether target knowledge is truly erased remains challenging. Existing output-level metrics fail to detect…
With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…
Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility. However, we find that existing methods often hallucinate, generate abnormal token sequences, or behave inconsistently, raising…
The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial prompting…
LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more explicit way by removing undesirable knowledge characterized…
Large Language Models' knowledge of how to perform cyber-security attacks, create bioweapons, and manipulate humans poses risks of misuse. Previous work has proposed methods to unlearn this knowledge. Historically, it has been unclear…
Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…
Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…
Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…