English
Related papers

Related papers: Steering Beyond the Support: Adversarial Training …

200 papers

Recent studies developed jailbreaking attacks, which construct jailbreaking prompts to fool LLMs into responding to harmful questions. Early-stage jailbreaking attacks require access to model internals or significant human efforts. More…

Cryptography and Security · Computer Science 2025-01-28 Xuan Chen , Yuzhou Nie , Wenbo Guo , Xiangyu Zhang

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

Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Georgios Pantazopoulos , Amit Parekh , Malvina Nikandrou , Alessandro Suglia

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions,…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Machine Learning · Computer Science 2025-01-22 Qizhang Li , Xiaochen Yang , Wangmeng Zuo , Yiwen Guo

Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, however, they remain critically vulnerable to jailbreak attacks that elicit harmful responses violating human values and safety guidelines.…

Cryptography and Security · Computer Science 2026-01-12 Zhaoqi Wang , Zijian Zhang , Daqing He , Pengtao Kou , Xin Li , Jiamou Liu , Jincheng An , Yong Liu

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Cryptography and Security · Computer Science 2024-04-15 Tianyu Zhang , Zixuan Zhao , Jiaqi Huang , Jingyu Hua , Sheng Zhong

Despite the outstanding performance of Large language Models (LLMs) in diverse tasks, they are vulnerable to jailbreak attacks, wherein adversarial prompts are crafted to bypass their security mechanisms and elicit unexpected responses.…

Cryptography and Security · Computer Science 2025-04-25 Zeqing He , Zhibo Wang , Zhixuan Chu , Huiyu Xu , Wenhui Zhang , Qinglong Wang , Rui Zheng

Learning models capable of providing reliable predictions in the face of adversarial actions has become a central focus of the machine learning community in recent years. This challenge arises from observing that data encountered at…

Machine Learning · Computer Science 2025-05-05 Marco C. Campi , Algo Carè , Luis G. Crespo , Simone Garatti , Federico A. Ramponi

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an…

Machine Learning · Computer Science 2026-02-03 Samuel Nellessen , Tal Kachman

Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's…

Cryptography and Security · Computer Science 2026-04-28 Xinhe Wang , Katia Sycara , Yaqi Xie

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

Imitation learning is a promising approach to end-to-end training of autonomous vehicle controllers. Typically the driving process with such approaches is entirely automatic and black-box, although in practice it is desirable to control the…

Robotics · Computer Science 2020-11-23 Renhao Wang , Adam Scibior , Frank Wood

An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or copyrighted information. In recent years, unlearning has…

Computation and Language · Computer Science 2024-11-06 Atakan Seyitoğlu , Aleksei Kuvshinov , Leo Schwinn , Stephan Günnemann

With the development of LLMs, the security threats of LLMs are getting more and more attention. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks primarily utilize scenario…

Cryptography and Security · Computer Science 2024-08-22 Zhiyuan Chang , Mingyang Li , Yi Liu , Junjie Wang , Qing Wang , Yang Liu

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Computation and Language · Computer Science 2025-11-26 Isack Lee , Haebin Seong

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Cryptography and Security · Computer Science 2025-07-15 William Hackett , Lewis Birch , Stefan Trawicki , Neeraj Suri , Peter Garraghan

This paper presents a safety-critical reinforcement learning framework for nonlinear dynamical systems with continuous state and input spaces operating under explicit physical constraints. Hard safety constraints are enforced independently…

Systems and Control · Electrical Eng. & Systems 2026-02-05 Hossein Rastgoftar

Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Chongxin Li , Hanzhang Wang , Lian Duan

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…

Artificial Intelligence · Computer Science 2024-06-17 Wei Zhao , Zhe Li , Yige Li , Ye Zhang , Jun Sun
‹ Prev 1 8 9 10 Next ›