English
Related papers

Related papers: In-Context Representation Hijacking

200 papers

We explore the ability of large language models (LLMs) to engage in subtle deception through strategically phrasing and intentionally manipulating information. This harmful behavior can be hard to detect, unlike blatant lying or…

Computation and Language · Computer Science 2025-10-02 Atharvan Dogra , Krishna Pillutla , Ameet Deshpande , Ananya B Sai , John Nay , Tanmay Rajpurohit , Ashwin Kalyan , Balaraman Ravindran

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. However, existing methods often struggle to balance semantic…

Computation and Language · Computer Science 2025-03-12 Zonghao Ying , Deyue Zhang , Zonglei Jing , Yisong Xiao , Quanchen Zou , Aishan Liu , Siyuan Liang , Xiangzheng Zhang , Xianglong Liu , Dacheng Tao

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

Cryptography and Security · Computer Science 2026-04-17 Zhengxian Wu , Juan Wen , Wanli Peng , Haowei Chang , Yinghan Zhou , Yiming Xue

Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms. Platforms routinely rely on LLMs for content moderation, asking them to label text based on disputed concepts like "hate…

Computers and Society · Computer Science 2026-03-09 Shira Gur-Arieh , Angelina Wang , Sina Fazelpour

While recent advancements in large language model (LLM) alignment have enabled the effective identification of malicious objectives involving scene nesting and keyword rewriting, our study reveals that these methods remain inadequate at…

Computation and Language · Computer Science 2024-10-10 Tianyu Wu , Lingrui Mei , Ruibin Yuan , Lujun Li , Wei Xue , Yike Guo

Researchers have explored different ways to improve large language models (LLMs)' capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but fail to leverage the inherent…

Computation and Language · Computer Science 2026-04-16 Zhichen Liu , Yongyuan Li , Yang Xu

Recent advances in large language models (LLMs) have intensified the need to understand and reliably curb their harmful behaviours. We introduce a multidimensional framework for probing and steering harmful content in model internals. For…

Artificial Intelligence · Computer Science 2025-07-30 McNair Shah , Saleena Angeline , Adhitya Rajendra Kumar , Naitik Chheda , Kevin Zhu , Vasu Sharma , Sean O'Brien , Will Cai

Current research on operator control of Large Language Models improves model robustness against adversarial attacks and misbehavior by training on preference examples, prompting, and input/output filtering. Despite good results, LLMs remain…

Artificial Intelligence · Computer Science 2025-12-03 Thomas Rivasseau

Despite recent advancements in Large Language Models (LLMs), their performance on tasks involving long contexts remains sub-optimal. In this work, we propose DoubleDipper, a novel In-Context-Learning method that automatically generates…

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibility of hijacking…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Changyue Li , Jiaying Li , Youliang Yuan , Jiaming He , Zhicong Huang , Pinjia He

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge, making them adaptable and cost-effective for various applications. However, the growing reliance on these systems also…

Cryptography and Security · Computer Science 2024-10-31 Yucheng Zhang , Qinfeng Li , Tianyu Du , Xuhong Zhang , Xinkui Zhao , Zhengwen Feng , Jianwei Yin

Large Language Models (LLMs) have transformed natural language processing and hold growing promise for advancing science, healthcare, and decision-making. Yet their training paradigms remain dominated by affirmation-based inference, akin to…

Artificial Intelligence · Computer Science 2025-12-05 Peter B. Walker , Hannah Davidson , Aiden Foster , Matthew Lienert , Thomas Pardue , Dale Russell

Natural Language Processing (NLP) models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling…

Machine Learning · Computer Science 2025-06-10 Kasimir Schulz , Kenneth Yeung , Kieran Evans

Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to bypass safety mechanisms. We show that such attacks are governed by a…

Artificial Intelligence · Computer Science 2026-05-08 Md Farhamdur Reza , Richeng Jin , Tianfu Wu , Huaiyu Dai

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Cryptography and Security · Computer Science 2026-04-28 Yuansen Liu , Yixuan Tang , Anthony Kum Hoe Tun

Prompting robots with natural language (NL) has largely been studied as what task to execute (goal selection, skill sequencing) rather than how to execute that task safely and efficiently in semantically rich, human-centric spaces. We…

Robotics · Computer Science 2025-11-18 Mani Amani , Behrad Beheshti , Reza Akhavian

Large Language Models (LLMs) have shown remarkable success in various tasks, yet their safety and the risk of generating harmful content remain pressing concerns. In this paper, we delve into the potential of In-Context Learning (ICL) to…

Machine Learning · Computer Science 2024-05-28 Zeming Wei , Yifei Wang , Ang Li , Yichuan Mo , Yisen Wang

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

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou