English
Related papers

Related papers: Steering Beyond the Support: Adversarial Training …

200 papers

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Cryptography and Security · Computer Science 2026-05-20 Hongyu Cai , Arjun Arunasalam , Yiming Liang , Antonio Bianchi , Z. Berkay Celik

This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We observe that existing defense mechanisms fail to generalize to harmful queries disguised by…

Machine Learning · Computer Science 2025-10-10 Weisen Jiang , Sinno Jialin Pan

Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…

Computation and Language · Computer Science 2024-10-08 Sarah Ball , Frauke Kreuter , Nina Panickssery

Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new…

Computation and Language · Computer Science 2024-06-10 Yihan Wang , Zhouxing Shi , Andrew Bai , Cho-Jui Hsieh

Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness." We investigate the mechanisms underlying…

Machine Learning · Computer Science 2026-05-18 Uzay Macar , Li Yang , Atticus Wang , Peter Wallich , Emmanuel Ameisen , Jack Lindsey

As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…

Cryptography and Security · Computer Science 2025-11-19 Hajun Kim , Hyunsik Na , Daeseon Choi

Adversarial lateral movement via compromised accounts remains difficult to discover via traditional rule-based defenses because it generally lacks explicit indicators of compromise. We propose a behavior-based, unsupervised framework…

Cryptography and Security · Computer Science 2021-08-06 Brian A. Powell

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Cryptography and Security · Computer Science 2025-10-21 Zhengyue Zhao , Yingzi Ma , Somesh Jha , Marco Pavone , Patrick McDaniel , Chaowei Xiao

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Zonghao Ying , Moyang Chen , Nizhang Li , Zhiqiang Wang , Wenxin Zhang , Quanchen Zou , Zonglei Jing , Aishan Liu , Xianglong Liu

Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is important to anticipate the range of potential Jailbreak attacks…

Cryptography and Security · Computer Science 2025-02-24 Pedram Zaree , Md Abdullah Al Mamun , Quazi Mishkatul Alam , Yue Dong , Ihsen Alouani , Nael Abu-Ghazaleh

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering,…

Cryptography and Security · Computer Science 2026-05-12 Yulong Chen , Qi Zhang , Jiawen Zhang , Yadong Liu , Mu Li , Jie Wen , Yong Xu

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

Machine Learning · Computer Science 2026-04-15 Shaopeng Fu , Di Wang

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from…

Artificial Intelligence · Computer Science 2025-09-30 Zhaoqi Wang , Daqing He , Zijian Zhang , Xin Li , Liehuang Zhu , Meng Li , Jiamou Liu

Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…

Cryptography and Security · Computer Science 2026-02-17 Shang Liu , Hanyu Pei , Zeyan Liu

Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic evolution of risk during decoding. This oversight leaves risk signals embedded in decoding…

Cryptography and Security · Computer Science 2026-04-10 Cheng Liu , Xiaolei Liu , Xingyu Li , Bangzhou Xin , Kangyi Ding

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Cryptography and Security · Computer Science 2026-03-23 Shawn Li , Yue Zhao

Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a substantial threat to LLM security. Current strategies for…

Cryptography and Security · Computer Science 2024-06-07 Lin Lu , Hai Yan , Zenghui Yuan , Jiawen Shi , Wenqi Wei , Pin-Yu Chen , Pan Zhou

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new…

Cryptography and Security · Computer Science 2025-08-12 Ivan Zhang

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…

Cryptography and Security · Computer Science 2026-01-06 Jirui Yang , Zheyu Lin , Zhihui Lu , Yinggui Wang , Lei Wang , Tao Wei , Qiang Duan , Xin Du , Shuhan Yang