English
Related papers

Related papers: Obfuscated Activations Bypass LLM Latent-Space Def…

200 papers

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Computation and Language · Computer Science 2025-05-13 Brian R. Y. Huang , Maximilian Li , Leonard Tang

Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc. However, recent…

Artificial Intelligence · Computer Science 2017-07-12 Atul Kumar , Sameep Mehta

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Computation and Language · Computer Science 2025-11-04 Peng Ding , Jun Kuang , Wen Sun , Zongyu Wang , Xuezhi Cao , Xunliang Cai , Jiajun Chen , Shujian Huang

Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic…

Computation and Language · Computer Science 2025-05-28 Wenbo Pan , Zhichao Liu , Qiguang Chen , Xiangyang Zhou , Haining Yu , Xiaohua Jia

With the widespread adoption of Large Language Models (LLMs), jailbreak attacks have become an increasingly pressing safety concern. While safety-aligned LLMs can effectively defend against normal harmful queries, they remain vulnerable to…

Computation and Language · Computer Science 2025-04-21 Yu Li , Han Jiang , Zhihua Wei

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that…

Computation and Language · Computer Science 2026-02-05 Zhexin Zhang , Yida Lu , Junfeng Fang , Junxiao Yang , Shiyao Cui , Hao Zhou , Fandong Meng , Jie Zhou , Hongning Wang , Minlie Huang , Tat-Seng Chua

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

Artificial Intelligence · Computer Science 2025-09-25 Huizhen Shu , Xuying Li , Zhuo Li

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

Computation and Language · Computer Science 2025-05-16 Michael Fire , Yitzhak Elbazis , Adi Wasenstein , Lior Rokach

LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…

Cryptography and Security · Computer Science 2025-11-18 Zesen Liu , Zhixiang Zhang , Yuchong Xie , Dongdong She

Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, yet at other times seem unable to recognize those strategies that govern their behavior. This suggests a limited degree of metacognition -…

Artificial Intelligence · Computer Science 2025-10-27 Li Ji-An , Hua-Dong Xiong , Robert C. Wilson , Marcelo G. Mattar , Marcus K. Benna

Adversarial attacks in computer vision exploit the vulnerabilities of machine learning models by introducing subtle perturbations to input data, often leading to incorrect predictions or classifications. These attacks have evolved in…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Vishal Asnani , Xi Yin , Xiaoming Liu

As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…

Cryptography and Security · Computer Science 2018-07-16 Tianwei Zhang , Zecheng He , Ruby B. Lee

Although deep generative models such as Defense-GAN and Defense-VAE have made significant progress in terms of adversarial defenses of image classification neural networks, several methods have been found to circumvent these defenses. Based…

Cryptography and Security · Computer Science 2020-11-04 Frederick Morlock , Dingsu Wang

Computer network defence is a complicated task that has necessitated a high degree of human involvement. However, with recent advancements in machine learning, fully autonomous network defence is becoming increasingly plausible. This paper…

Cryptography and Security · Computer Science 2023-06-16 Myles Foley , Mia Wang , Zoe M , Chris Hicks , Vasilios Mavroudis

As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become a critical area of research. Traditional methods rely…

Computation and Language · Computer Science 2024-11-06 Yuxin Xiao , Chaoqun Wan , Yonggang Zhang , Wenxiao Wang , Binbin Lin , Xiaofei He , Xu Shen , Jieping Ye

To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by…

Cryptography and Security · Computer Science 2024-05-08 Shang Shang , Xinqiang Zhao , Zhongjiang Yao , Yepeng Yao , Liya Su , Zijing Fan , Xiaodan Zhang , Zhengwei Jiang

Graphical user interface (GUI) agents built on multimodal large language models (MLLMs) have recently demonstrated strong decision-making abilities in screen-based interaction tasks. However, they remain highly vulnerable to pop-up-based…

Cryptography and Security · Computer Science 2026-04-08 Zihe Yan , Jiaping Gui , Zhuosheng Zhang , Gongshen Liu

We introduce a formal notion of defendability against backdoors using a game between an attacker and a defender. In this game, the attacker modifies a function to behave differently on a particular input known as the "trigger", while…

Machine Learning · Computer Science 2025-02-12 Paul Christiano , Jacob Hilton , Victor Lecomte , Mark Xu

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and…

Cryptography and Security · Computer Science 2024-12-03 Jing Cui , Yishi Xu , Zhewei Huang , Shuchang Zhou , Jianbin Jiao , Junge Zhang

Anomaly detection is a method for discovering unusual and suspicious behavior. In many real-world scenarios, the examined events can be directly linked to the actions of an adversary, such as attacks on computer networks or frauds in…

Machine Learning · Computer Science 2020-04-23 Olga Petrova , Karel Durkota , Galina Alperovich , Karel Horak , Michal Najman , Branislav Bosansky , Viliam Lisy