English
Related papers

Related papers: Inference-Time Backdoors via Chat Templates: From …

200 papers

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

Cryptography and Security · Computer Science 2026-05-12 Wei Zhao , Zhe Li , Peixin Zhang , Jun Sun

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

Cryptography and Security · Computer Science 2017-12-18 Xinyun Chen , Chang Liu , Bo Li , Kimberly Lu , Dawn Song

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Cryptography and Security · Computer Science 2026-04-22 Kun Wang , Cheng Qian , Miao Yu , Lilan Peng , Liang Lin , Jiaming Zhang , Tianyu Zhang , Yu Cheng , Yang Wang

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Cryptography and Security · Computer Science 2026-03-18 Ali Raza , Gurang Gupta , Nikolay Matyunin , Jibesh Patra

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…

Cryptography and Security · Computer Science 2025-06-12 Li Changjiang , Liang Jiacheng , Cao Bochuan , Chen Jinghui , Wang Ting

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

Artificial Intelligence · Computer Science 2026-05-07 Chenglin Yang

The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or…

Machine Learning · Computer Science 2025-05-27 Shijie Liu , Andrew C. Cullen , Paul Montague , Sarah Erfani , Benjamin I. P. Rubinstein

This paper proposes a novel backdoor threat attacking the LLM-as-a-Judge evaluation regime, where the adversary controls both the candidate and evaluator model. The backdoored evaluator victimizes benign users by unfairly assigning inflated…

Computation and Language · Computer Science 2025-03-04 Terry Tong , Fei Wang , Zhe Zhao , Muhao Chen

In the era of rapid generative AI development, interactions with large language models (LLMs) pose increasing risks of misuse. Prior research has primarily focused on attacks using template-based prompts and optimization-oriented methods,…

Cryptography and Security · Computer Science 2026-03-03 Wenhan Chang , Tianqing Zhu , Yu Zhao , Shuangyong Song , Ping Xiong , Wanlei Zhou

When an adversary provides poison samples to a machine learning model, privacy leakage, such as membership inference attacks that infer whether a sample was included in the training of the model, becomes effective by moving the sample to an…

Cryptography and Security · Computer Science 2023-03-23 Yumeki Goto , Nami Ashizawa , Toshiki Shibahara , Naoto Yanai

While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable to prompt injection attacks: malicious third party prompts that subvert the intent of the system designer. To help researchers…

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Multiagent Systems · Computer Science 2026-05-12 Xiaolin Sun , Zixuan Liu , Yibin Hu , Zizhan Zheng

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Artificial Intelligence · Computer Science 2025-05-20 Yige Li , Hanxun Huang , Yunhan Zhao , Xingjun Ma , Jun Sun

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Cryptography and Security · Computer Science 2022-10-20 Yangyi Chen , Fanchao Qi , Hongcheng Gao , Zhiyuan Liu , Maosong Sun

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Cryptography and Security · Computer Science 2025-09-10 Bilal Hussain Abbasi , Yanjun Zhang , Leo Zhang , Shang Gao

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and…

Cryptography and Security · Computer Science 2024-10-30 Wenkai Yang , Xiaohan Bi , Yankai Lin , Sishuo Chen , Jie Zhou , Xu Sun

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this…

Cryptography and Security · Computer Science 2026-02-26 David Schmotz , Luca Beurer-Kellner , Sahar Abdelnabi , Maksym Andriushchenko

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Cryptography and Security · Computer Science 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

Cryptography and Security · Computer Science 2026-04-28 Richard Joseph Mitchell
‹ Prev 1 3 4 5 6 7 10 Next ›