English
Related papers

Related papers: The Missing Half: Unveiling Training-time Implicit…

200 papers

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high clean accuracy in…

Machine Learning · Computer Science 2023-01-24 Soumyadeep Pal , Ren Wang , Yuguang Yao , Sijia Liu

Large language models (LLMs) are increasingly used for decision-making tasks under uncertainty; however, their risk profiles and how they are influenced by prompting and alignment methods remain underexplored. Existing studies have…

Artificial Intelligence · Computer Science 2025-10-08 Yikai Wang , Xiaocheng Li , Guanting Chen

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Computation and Language · Computer Science 2026-05-15 Yu Fu , Haz Sameen Shahgir , Huanli Gong , Zhipeng Wei , N. Benjamin Erichson , Yue Dong

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Machine Learning · Computer Science 2020-11-24 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

Decentralized training has become a resource-efficient framework to democratize the training of large language models (LLMs). However, the privacy risks associated with this framework, particularly due to the potential inclusion of…

Cryptography and Security · Computer Science 2025-02-25 Chenxi Dai , Lin Lu , Pan Zhou

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Cryptography and Security · Computer Science 2026-04-02 Anubhab Sahu , Diptisha Samanta , Reza Soosahabi

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on…

Cryptography and Security · Computer Science 2026-04-07 Charafeddine Mouzouni

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

Software Engineering · Computer Science 2024-03-06 Aftab Hussain , Md Rafiqul Islam Rabin , Navid Ayoobi , Mohammad Amin Alipour

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to…

We show that iterative deployment of large language models (LLMs), each fine-tuned on data carefully curated by users from the previous models' deployment, can significantly change the properties of the resultant models. By testing this…

Artificial Intelligence · Computer Science 2026-01-01 Augusto B. Corrêa , Yoav Gelberg , Luckeciano C. Melo , Ilia Shumailov , André G. Pereira , Yarin Gal

The integration of large language models (LLMs) into cyber security applications presents both opportunities and critical safety risks. We introduce CyberLLMInstruct, a dataset of 54,928 pseudo-malicious instruction-response pairs spanning…

Cryptography and Security · Computer Science 2025-09-18 Adel ElZemity , Budi Arief , Shujun Li

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 systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…

Artificial Intelligence · Computer Science 2026-05-08 Jonas Wiedermann-Möller , Leonard Dung , Maksym Andriushchenko

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Computation and Language · Computer Science 2024-03-05 Yue Deng , Wenxuan Zhang , Sinno Jialin Pan , Lidong Bing

The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are…

Artificial Intelligence · Computer Science 2024-07-02 Niloofar Mireshghallah , Hyunwoo Kim , Xuhui Zhou , Yulia Tsvetkov , Maarten Sap , Reza Shokri , Yejin Choi

Tool learning is widely acknowledged as a foundational approach or deploying large language models (LLMs) in real-world scenarios. While current research primarily emphasizes leveraging tools to augment LLMs, it frequently neglects emerging…

Computation and Language · Computer Science 2024-08-19 Junjie Ye , Sixian Li , Guanyu Li , Caishuang Huang , Songyang Gao , Yilong Wu , Qi Zhang , Tao Gui , Xuanjing Huang

In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment…

Machine Learning · Computer Science 2020-12-15 Ksenia Konyushkova , Konrad Zolna , Yusuf Aytar , Alexander Novikov , Scott Reed , Serkan Cabi , Nando de Freitas

Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…

Machine Learning · Computer Science 2025-08-05 Yuetian Chen , Zhiqi Wang , Nathalie Baracaldo , Swanand Ravindra Kadhe , Lei Yu

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…

Cryptography and Security · Computer Science 2025-05-06 Kang Chen , Xiuze Zhou , Yuanguo Lin , Shibo Feng , Li Shen , Pengcheng Wu
‹ Prev 1 4 5 6 7 8 10 Next ›