English
Related papers

Related papers: The WMDP Benchmark: Measuring and Reducing Malicio…

200 papers

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…

Machine Learning · Computer Science 2025-06-03 Jakub Łucki , Boyi Wei , Yangsibo Huang , Peter Henderson , Florian Tramèr , Javier Rando

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…

Computation and Language · Computer Science 2025-06-12 Bang An , Sicheng Zhu , Ruiyi Zhang , Michael-Andrei Panaitescu-Liess , Yuancheng Xu , Furong Huang

Large Language Models (LLMs), such as ChatGPT, have achieved impressive milestones in natural language processing (NLP). Despite their impressive performance, the models are known to pose important risks. As these models are deployed in…

Computation and Language · Computer Science 2023-10-06 Ke Shen , Mayank Kejriwal

Unlearning aims to remove copyrighted, sensitive, or private content from large language models (LLMs) without a full retraining. In this work, we develop a multi-task unlearning benchmark (LUME) which features three tasks: (1) unlearn…

Computation and Language · Computer Science 2025-02-28 Anil Ramakrishna , Yixin Wan , Xiaomeng Jin , Kai-Wei Chang , Zhiqi Bu , Bhanukiran Vinzamuri , Volkan Cevher , Mingyi Hong , Rahul Gupta

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…

Computation and Language · Computer Science 2026-01-21 Tyler Lizzo , Larry Heck

Several recent works have argued that Large Language Models (LLMs) can be used to tame the data deluge in the cybersecurity field, by improving the automation of Cyber Threat Intelligence (CTI) tasks. This work presents an evaluation…

Cryptography and Security · Computer Science 2025-11-13 Emanuele Mezzi , Fabio Massacci , Katja Tuma

Machine unlearning can be useful for removing harmful capabilities and memorized text from large language models (LLMs), but there are not yet standardized methods for rigorously evaluating it. In this paper, we first survey techniques and…

Computation and Language · Computer Science 2024-02-27 Aengus Lynch , Phillip Guo , Aidan Ewart , Stephen Casper , Dylan Hadfield-Menell

This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a principled approach to removing the influence of undesirable data…

Computation and Language · Computer Science 2025-06-03 Jiahui Geng , Qing Li , Herbert Woisetschlaeger , Zongxiong Chen , Fengyu Cai , Yuxia Wang , Preslav Nakov , Hans-Arno Jacobsen , Fakhri Karray

Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…

Machine Learning · Computer Science 2024-10-02 Xuefeng Du , Reshmi Ghosh , Robert Sim , Ahmed Salem , Vitor Carvalho , Emily Lawton , Yixuan Li , Jack W. Stokes

With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), including content generation, human-computer interaction, machine translation, and…

Computation and Language · Computer Science 2025-10-31 Songyang Liu , Chaozhuo Li , Jiameng Qiu , Xi Zhang , Feiran Huang , Litian Zhang , Yiming Hei , Philip S. Yu

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

Cryptography and Security · Computer Science 2025-09-10 Hongfei Xia , Hongru Wang , Zeming Liu , Qian Yu , Yuhang Guo , Haifeng Wang

Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase…

Computation and Language · Computer Science 2024-10-08 Bozhong Tian , Xiaozhuan Liang , Siyuan Cheng , Qingbin Liu , Mengru Wang , Dianbo Sui , Xi Chen , Huajun Chen , Ningyu Zhang

Recent developments in Large Language Model (LLM) capabilities have brought great potential but also posed new risks. For example, LLMs with knowledge of bioweapons, advanced chemistry, or cyberattacks could cause violence if placed in the…

Machine Learning · Computer Science 2025-03-17 Matthew Khoriaty , Andrii Shportko , Gustavo Mercier , Zach Wood-Doughty

The advent of Large Language Models (LLMs) has revolutionized various applications by providing advanced natural language processing capabilities. However, this innovation introduces new cybersecurity challenges. This paper explores the…

Cryptography and Security · Computer Science 2024-06-18 Stephen Burabari Tete

Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements. Once these risks emerge, timely updates are crucial to remove undesirable responses, ensuring legal and…

Machine Learning · Computer Science 2025-02-27 Qizhou Wang , Jin Peng Zhou , Zhanke Zhou , Saebyeol Shin , Bo Han , Kilian Q. Weinberger

The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…

Computation and Language · Computer Science 2024-10-29 Sahasra Kokkula , Somanathan R , Nandavardhan R , Aashishkumar , G Divya

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as…

Artificial Intelligence · Computer Science 2026-03-13 Raj Sanjay Shah , Jing Huang , Keerthiram Murugesan , Nathalie Baracaldo , Diyi Yang

Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safety- and security-related threats and vulnerabilities of LLMs,…

Computation and Language · Computer Science 2023-08-25 Maximilian Mozes , Xuanli He , Bennett Kleinberg , Lewis D. Griffin

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely…

Computation and Language · Computer Science 2025-10-20 Zhiqiang Kou , Junyang Chen , Xin-Qiang Cai , Ming-Kun Xie , Biao Liu , Changwei Wang , Lei Feng , Yuheng Jia , Gang Niu , Masashi Sugiyama , Xin Geng

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…