English
Related papers

Related papers: NeuroStrike: Neuron-Level Attacks on Aligned LLMs

200 papers

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Computation and Language · Computer Science 2025-08-26 Paul Darm , Annalisa Riccardi

While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…

Computation and Language · Computer Science 2024-03-01 Nan Xu , Fei Wang , Ben Zhou , Bang Zheng Li , Chaowei Xiao , Muhao Chen

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

Machine Learning · Computer Science 2026-04-24 Chengcan Wu , Zhixin Zhang , Zeming Wei , Yihao Zhang , Xiaokun Luan , Meng Sun

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Cryptography and Security · Computer Science 2025-11-13 Daniyal Ganiuly , Assel Smaiyl

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and…

Computation and Language · Computer Science 2024-10-29 Rima Hazra , Sayan Layek , Somnath Banerjee , Soujanya Poria

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Cryptography and Security · Computer Science 2025-10-24 Shuo Chen , Zhen Han , Haokun Chen , Bailan He , Shengyun Si , Jingpei Wu , Philip Torr , Volker Tresp , Jindong Gu

Reasoning has been a central topic in artificial intelligence from the beginning. The recent progress made on distributed representation and neural networks continues to improve the state-of-the-art performance of natural language…

Computation and Language · Computer Science 2024-10-14 Zi'ou Zheng , Xiaodan Zhu

Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment…

Machine Learning · Computer Science 2026-01-08 Shuo Yang , Qihui Zhang , Yuyang Liu , Xiaojun Jia , Kunpeng Ning , Jiayu Yao , Jigang Wang , Hailiang Dai , Yibing Song , Li Yuan

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Large language models (LLMs) have significantly influenced various industries but suffer from a critical flaw, the potential sensitivity of generating harmful content, which poses severe societal risks. We developed and tested novel attack…

Computation and Language · Computer Science 2025-02-25 Yuyi Huang , Runzhe Zhan , Derek F. Wong , Lidia S. Chao , Ailin Tao

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Cryptography and Security · Computer Science 2024-10-08 Yiting Dong , Guobin Shen , Dongcheng Zhao , Xiang He , Yi Zeng

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

Cryptography and Security · Computer Science 2026-05-20 Ye Sun , Xin Wang , Jiaming Zhang , Yifeng Gao , Yixu Wang , Yifan Ding , Qixian Zhang , Henghui Ding , Xingjun Ma , Yu-Gang Jiang

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techniques, while…

Cryptography and Security · Computer Science 2024-12-12 Yuxi Li , Zhibo Zhang , Kailong Wang , Ling Shi , Haoyu Wang

Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing safety alignment techniques primarily focus on pretraining, leaving fine-tuned models…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Truyen Tran

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Cryptography and Security · Computer Science 2026-04-30 Zheng-Xin Yong , Stephen H. Bach

Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven…

Cryptography and Security · Computer Science 2026-03-10 Neha Nagaraja , Hayretdin Bahsi

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Computation and Language · Computer Science 2025-04-15 Yutao Mou , Yuxiao Luo , Shikun Zhang , Wei Ye

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.…

Cryptography and Security · Computer Science 2026-05-19 Tim Beyer , Sophie Xhonneux , Simon Geisler , Gauthier Gidel , Leo Schwinn , Stephan Günnemann

Despite being empowered with alignment mechanisms, large language models (LLMs) are increasingly vulnerable to emerging jailbreak attacks that can compromise their alignment mechanisms. This vulnerability poses significant risks to…

Computation and Language · Computer Science 2025-04-15 Shaoqing Zhang , Zhuosheng Zhang , Kehai Chen , Rongxiang Weng , Muyun Yang , Tiejun Zhao , Min Zhang

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Cryptography and Security · Computer Science 2026-05-19 Tsafac Nkombong Regine Cyrille , Franziska Schwarz