English
Related papers

Related papers: Latent Adversarial Detection: Adaptive Probing of …

200 papers

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Artificial Intelligence · Computer Science 2026-05-05 Sheldon Yu , Yingcheng Sun , Hanqing Guo , Julian McAuley , Qianqian Tong

Multi-turn prompt injection attacks distribute malicious intent across multiple conversation turns, exploiting the assumption that each turn is evaluated independently. While single-turn detection has been extensively studied, no published…

Cryptography and Security · Computer Science 2026-03-09 J Alex Corll

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

Cryptography and Security · Computer Science 2026-03-03 Oluseyi Olukola , Nick Rahimi

Large language models (LLMs) aligned for safety through techniques like reinforcement learning from human feedback (RLHF) often exhibit emergent deceptive behaviors, where outputs appear compliant but subtly mislead or omit critical…

Machine Learning · Computer Science 2025-07-15 Santhosh Kumar Ravindran

As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluations fail to…

Computation and Language · Computer Science 2026-05-29 Xiangzhe Yuan , Zhenhao Zhang , Haoming Tang , Siying Hu

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Computation and Language · Computer Science 2024-06-12 Fan Liu , Zhao Xu , Hao Liu

Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions while real-world attacks unfold through adaptive multi-turn…

Computation and Language · Computer Science 2025-12-23 Aashray Reddy , Andrew Zagula , Nicholas Saban

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Cryptography and Security · Computer Science 2024-11-04 Qizhang Li , Yiwen Guo , Wangmeng Zuo , Hao Chen

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…

Cryptography and Security · Computer Science 2025-05-26 Weiyang Guo , Jing Li , Wenya Wang , YU LI , Daojing He , Jun Yu , Min Zhang

Large language models, LLMs, are increasingly deployed in multiturn settings where earlier responses shape later ones, making reliability dependent on whether a conversation remains consistent over time. When this consistency degrades…

Computation and Language · Computer Science 2026-04-20 Wael Hafez , Amir Nazeri

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…

Machine Learning · Computer Science 2025-10-07 Taeyoung Yun , Pierre-Luc St-Charles , Jinkyoo Park , Yoshua Bengio , Minsu Kim

Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlooks the high-dimensional, relational, and nonlinear geometry of model representations. We apply…

Machine Learning · Computer Science 2026-04-27 Aideen Fay , Inés García-Redondo , Qiquan Wang , Haim Dubossarsky , Anthea Monod

Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, each agent exhibits…

Cryptography and Security · Computer Science 2026-05-11 Taein Lim , Seongyong Ju , Munhyeok Kim , Hyunjun Kim , Hoki Kim

Turn-level metrics are widely used to evaluate properties of multi-turn human-LLM conversations, from safety and sycophancy to dialogue quality. However, consecutive turns within a conversation are not statistically independent -- a fact…

Computation and Language · Computer Science 2026-04-17 Ferdinand M. Schessl

Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in conversational LLMs: turn amplification, in which a model consistently prolongs multi-turn…

Machine Learning · Computer Science 2026-02-23 Zachary Coalson , Bo Fang , Sanghyun Hong

While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of disconnected events. This lack of temporal awareness facilitates a "Safety Gap" where…

Artificial Intelligence · Computer Science 2026-02-20 Justin Albrethsen , Yash Datta , Kunal Kumar , Sharath Rajasekar

Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs…

Computation and Language · Computer Science 2025-04-07 Abhishek Singhania , Christophe Dupuy , Shivam Mangale , Amani Namboori

Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based multi-turn jailbreak methods learn long-horizon attack strategies from interaction…

Artificial Intelligence · Computer Science 2026-05-12 Zhida He , Xiaoyu Wen , Han Qi , Ziyuan Zhou , Peng Yu , Xingcheng Xu , Dongrui Liu , Xia Hu , Chaochao Lu , Qiaosheng Zhang

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Computation and Language · Computer Science 2023-05-30 Xuanjie Fang , Sijie Cheng , Yang Liu , Wei Wang
‹ Prev 1 2 3 10 Next ›