English
Related papers

Related papers: Red-teaming Activation Probes using Prompted LLMs

200 papers

Recently, red teaming, with roots in security, has become a key evaluative approach to ensure the safety and reliability of Generative Artificial Intelligence. However, most existing work emphasizes technical benchmarks and attack success…

Computers and Society · Computer Science 2026-02-24 Adriana Alvarado Garcia , Ruyuan Wan , Ozioma C. Oguine , Karla Badillo-Urquiola

Understanding the capabilities of text-to-image (T2I) models in harmful content generation is essential to safety and compliance. However, human red-teaming is costly and inconsistent, driving the need for automatic tools that simulate…

Machine Learning · Computer Science 2026-05-13 Zhi-Yi Chin , Pin-Yu Chen , Wei-Chen Chiu , Mario Fritz

Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they have increasingly turned to search-augmented LLMs to mitigate…

Computation and Language · Computer Science 2026-02-10 Yu Yan , Sheng Sun , Mingfeng Li , Zheming Yang , Chiwei Zhu , Fei Ma , Benfeng Xu , Min Liu , Qi Li

Red-teaming is a core part of the infrastructure that ensures that AI models do not produce harmful content. Unlike past technologies, the black box nature of generative AI systems necessitates a uniquely interactional mode of testing, one…

Many publicly available language models have been safety tuned to reduce the likelihood of toxic or liability-inducing text. To redteam or jailbreak these models for compliance with toxic requests, users and security analysts have developed…

Computation and Language · Computer Science 2024-10-02 T. Ben Thompson , Michael Sklar

Eliciting harmful behavior from large language models (LLMs) is an important task to ensure the proper alignment and safety of the models. Often when training LLMs, ethical guidelines are followed yet alignment failures may still be…

Cryptography and Security · Computer Science 2024-08-20 Robert J. Moss

As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vulnerabilities, they often rely heavily on human input and…

Cryptography and Security · Computer Science 2025-03-21 Andy Zhou , Kevin Wu , Francesco Pinto , Zhaorun Chen , Yi Zeng , Yu Yang , Shuang Yang , Sanmi Koyejo , James Zou , Bo Li

Deploying large language models (LMs) can pose hazards from harmful outputs such as toxic or false text. Prior work has introduced automated tools that elicit harmful outputs to identify these risks. While this is a valuable step toward…

Computation and Language · Computer Science 2023-10-12 Stephen Casper , Jason Lin , Joe Kwon , Gatlen Culp , Dylan Hadfield-Menell

Red teaming has evolved from its origins in military applications to become a widely adopted methodology in cybersecurity and AI. In this paper, we take a critical look at the practice of AI red teaming. We argue that despite its current…

Artificial Intelligence · Computer Science 2025-11-03 Subhabrata Majumdar , Brian Pendleton , Abhishek Gupta

Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…

Computation and Language · Computer Science 2023-12-11 Chengyuan Liu , Fubang Zhao , Lizhi Qing , Yangyang Kang , Changlong Sun , Kun Kuang , Fei Wu

The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them…

Machine Learning · Computer Science 2026-03-25 Chunxiao Li , Lijun Li , Jing Shao

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into…

Artificial Intelligence · Computer Science 2026-02-10 Alexander Panfilov , Paul Kassianik , Maksym Andriushchenko , Jonas Geiping

Large Language Models (LLMs) have gained increasing attention for their remarkable capacity, alongside concerns about safety arising from their potential to produce harmful content. Red teaming aims to find prompts that could elicit harmful…

Computation and Language · Computer Science 2025-02-25 Rui Li , Peiyi Wang , Jingyuan Ma , Di Zhang , Lei Sha , Zhifang Sui

Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and…

Artificial Intelligence · Computer Science 2025-09-10 Minghui Li , Hao Zhang , Yechao Zhang , Wei Wan , Shengshan Hu , pei Xiaobing , Jing Wang

With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may…

Computation and Language · Computer Science 2026-04-14 Yanxu Mao , Peipei Liu , Tiehan Cui , Congying Liu , Mingzhe Xing , Datao You

We introduce a group of related methods for binary classification tasks using probes of the hidden state activations in large language models (LLMs). Performance is on par with the largest and most advanced LLMs currently available, but…

Machine Learning · Computer Science 2024-08-22 John Scoville , Shang Gao , Devanshu Agrawal , Javed Qadrud-Din

Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI…

Artificial Intelligence · Computer Science 2026-05-20 Oussama Zenkri , Oliver Brock

Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains a critical, under-explored safety concern, posing a significant safety risk to real-world…

Robotics · Computer Science 2026-04-08 Baoshun Tong , Haoran He , Ling Pan , Yang Liu , Liang Lin

Red teaming assesses how large language models (LLMs) can produce content that violates norms, policies, and rules set during their safety training. However, most existing automated methods in the literature are not representative of the…

Despite their remarkable success, large language models (LLMs) have shown limited ability on safety-critical code tasks such as vulnerability detection. Typically, static analysis (SA) tools, like CodeQL, CodeGuru Security, etc., are used…

Cryptography and Security · Computer Science 2025-09-15 Ira Ceka , Feitong Qiao , Anik Dey , Aastha Valecha , Gail Kaiser , Baishakhi Ray