English
Related papers

Related papers: Sleeper Agents: Training Deceptive LLMs that Persi…

200 papers

Human communication is motivated: people speak, write, and create content with a particular communicative intent in mind. As a result, information that large language models (LLMs) and AI agents process is inherently framed by humans'…

Computation and Language · Computer Science 2026-02-03 Addison J. Wu , Ryan Liu , Kerem Oktar , Theodore R. Sumers , Thomas L. Griffiths

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Cryptography and Security · Computer Science 2026-03-17 Jianwei Li , Jung-Eun Kim

The objective of digital forgetting is, given a model with undesirable knowledge or behavior, obtain a new model where the detected issues are no longer present. The motivations for forgetting include privacy protection, copyright…

Cryptography and Security · Computer Science 2025-01-14 Alberto Blanco-Justicia , Najeeb Jebreel , Benet Manzanares , David Sánchez , Josep Domingo-Ferrer , Guillem Collell , Kuan Eeik Tan

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Cryptography and Security · Computer Science 2023-10-19 Ganghua Wang , Xun Xian , Jayanth Srinivasa , Ashish Kundu , Xuan Bi , Mingyi Hong , Jie Ding

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. We thus…

Machine Learning · Computer Science 2025-02-06 Nicholas Goldowsky-Dill , Bilal Chughtai , Stefan Heimersheim , Marius Hobbhahn

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Cryptography and Security · Computer Science 2026-05-12 Matteo Lupinacci , Francesco Aurelio Pironti , Francesco Blefari , Francesco Romeo , Luigi Arena , Angelo Furfaro

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Cryptography and Security · Computer Science 2026-03-03 Zhihang Deng , Jiaping Gui , Weinan Zhang

Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embed surgically modified samples with targeted labels in the…

Cryptography and Security · Computer Science 2019-03-19 Zhaoyuan Yang , Naresh Iyer , Johan Reimann , Nurali Virani

The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…

Computation and Language · Computer Science 2023-10-20 Zhouxing Shi , Yihan Wang , Fan Yin , Xiangning Chen , Kai-Wei Chang , Cho-Jui Hsieh

Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently…

Computation and Language · Computer Science 2025-09-23 Qingyu Lu , Liang Ding , Siyi Cao , Xuebo Liu , Kanjian Zhang , Jinxia Zhang , Dacheng Tao

The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates a cooperative backdoor attack in a decentralized…

Machine Learning · Computer Science 2024-05-27 Mengtong Gao , Yifei Zou , Zuyuan Zhang , Xiuzhen Cheng , Dongxiao Yu

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt…

Large Language Models (LLMs) are becoming vital tools that help us solve and understand complex problems by acting as digital assistants. LLMs can generate convincing explanations, even when only given the inputs and outputs of these…

Computation and Language · Computer Science 2024-10-14 Rohan Ajwani , Shashidhar Reddy Javaji , Frank Rudzicz , Zining Zhu

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In…

Computation and Language · Computer Science 2025-12-16 Jiachen Zhao , Jing Huang , Zhengxuan Wu , David Bau , Weiyan Shi

Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often…

Machine Learning · Computer Science 2025-03-25 Sharon Lin , Krishnamurthy , Dvijotham , Jamie Hayes , Chongyang Shi , Ilia Shumailov , Shuang Song

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Machine Learning · Statistics 2019-12-10 Alexander Turner , Dimitris Tsipras , Aleksander Madry

Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a…

Machine Learning · Computer Science 2024-11-12 Shafi Goldwasser , Michael P. Kim , Vinod Vaikuntanathan , Or Zamir

The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing…

Cryptography and Security · Computer Science 2026-04-24 Jiali Wei , Ming Fan , Guoheng Sun , Xicheng Zhang , Haijun Wang , Ting Liu

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Computation and Language · Computer Science 2026-04-21 Dang Huu-Tien , Hoang Thanh-Tung , Anh Bui , Minh-Phuong Nguyen , Le-Minh Nguyen , Naoya Inoue
‹ Prev 1 8 9 10 Next ›