English
Related papers

Related papers: Jailbreaking as a Reward Misspecification Problem

200 papers

Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety mechanisms may not be comprehensive, leaving potential…

Cryptography and Security · Computer Science 2024-11-06 Emet Bethany , Mazal Bethany , Juan Arturo Nolazco Flores , Sumit Kumar Jha , Peyman Najafirad

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…

Machine Learning · Computer Science 2025-03-06 Erfan Entezami , Ali Naseh

Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities, especially in model API. To fill the research gap, we carry out the…

Cryptography and Security · Computer Science 2024-01-23 Yuanwei Wu , Xiang Li , Yixin Liu , Pan Zhou , Lichao Sun

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Cryptography and Security · Computer Science 2024-12-03 Erick Galinkin , Martin Sablotny

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…

Cryptography and Security · Computer Science 2026-03-04 Kalyan Nakka , Nitesh Saxena

Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of "jailbreaking",…

Cryptography and Security · Computer Science 2024-09-02 Sibo Yi , Yule Liu , Zhen Sun , Tianshuo Cong , Xinlei He , Jiaxing Song , Ke Xu , Qi Li

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Computation and Language · Computer Science 2025-04-18 Charlotte Siska , Anush Sankaran

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…

Cryptography and Security · Computer Science 2024-12-23 Hongyi Li , Jiawei Ye , Jie Wu , Tianjie Yan , Chu Wang , Zhixin Li

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential…

Cryptography and Security · Computer Science 2025-06-10 Yingchaojie Feng , Zhizhang Chen , Zhining Kang , Sijia Wang , Haoyu Tian , Wei Zhang , Minfeng Zhu , Wei Chen

Misalignment in Large Language Models (LLMs) refers to the failure to simultaneously satisfy safety, value, and cultural dimensions, leading to behaviors that diverge from human expectations in real-world settings where these dimensions…

Computation and Language · Computer Science 2026-02-12 Usman Naseem , Gautam Siddharth Kashyap , Ebad Shabbir , Sushant Kumar Ray , Abdullah Mohammad , Rafiq Ali

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Cryptography and Security · Computer Science 2025-09-19 Yuanbo Xie , Yingjie Zhang , Tianyun Liu , Duohe Ma , Tingwen Liu

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Computation and Language · Computer Science 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad

Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit harmful responses. As such, we present AutoAdv, a novel…

Cryptography and Security · Computer Science 2025-12-25 Aashray Reddy , Andrew Zagula , Nicholas Saban

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Cryptography and Security · Computer Science 2024-06-14 Xuan Chen , Yuzhou Nie , Lu Yan , Yunshu Mao , Wenbo Guo , Xiangyu Zhang

In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (LLMs). Despite rigorous pretraining and finetuning focused on…

Cryptography and Security · Computer Science 2024-12-02 Peiran Wang , Xiaogeng Liu , Chaowei Xiao

Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such…

Computation and Language · Computer Science 2024-05-08 Hongyu Cai , Arjun Arunasalam , Leo Y. Lin , Antonio Bianchi , Z. Berkay Celik

Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) can become a single point of failure when it fails to penalize…

Artificial Intelligence · Computer Science 2026-04-22 Jiacheng Liang , Yao Ma , Tharindu Kumarage , Satyapriya Krishna , Rahul Gupta , Kai-Wei Chang , Aram Galstyan , Charith Peris

Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…

Cryptography and Security · Computer Science 2024-06-21 Jiongxiao Wang , Jiazhao Li , Yiquan Li , Xiangyu Qi , Junjie Hu , Yixuan Li , Patrick McDaniel , Muhao Chen , Bo Li , Chaowei Xiao

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a model's safety, especially for MLPs in end-of-sentence…

Computation and Language · Computer Science 2024-10-15 Yifan Luo , Zhennan Zhou , Meitan Wang , Bin Dong