English
Related papers

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

200 papers

Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However,…

Cryptography and Security · Computer Science 2025-07-08 Alberto Castagnaro , Umberto Salviati , Mauro Conti , Luca Pajola , Simeone Pizzi

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

Cryptography and Security · Computer Science 2023-05-08 Kai Greshake , Sahar Abdelnabi , Shailesh Mishra , Christoph Endres , Thorsten Holz , Mario Fritz

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Machine Learning · Computer Science 2025-05-30 Xiangyu Zhou , Yao Qiang , Saleh Zare Zade , Mohammad Amin Roshani , Prashant Khanduri , Douglas Zytko , Dongxiao Zhu

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

Artificial Intelligence · Computer Science 2026-01-08 Kanghua Mo , Li Hu , Yucheng Long , Zhihao Li

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to…

Cryptography and Security · Computer Science 2026-02-17 Lukas Struppek , Adam Gleave , Kellin Pelrine

Generative large language models are crucial in natural language processing, but they are vulnerable to backdoor attacks, where subtle triggers compromise their behavior. Although backdoor attacks against LLMs are constantly emerging,…

Cryptography and Security · Computer Science 2025-02-27 Xuxu Liu , Siyuan Liang , Mengya Han , Yong Luo , Aishan Liu , Xiantao Cai , Zheng He , Dacheng Tao

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Computation and Language · Computer Science 2021-01-18 Lichao Sun

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Multiagent Systems · Computer Science 2025-10-10 Rana Muhammad Shahroz Khan , Zhen Tan , Sukwon Yun , Charles Fleming , Tianlong Chen

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is…

Computation and Language · Computer Science 2021-06-14 Fanchao Qi , Yuan Yao , Sophia Xu , Zhiyuan Liu , Maosong Sun

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

Cryptography and Security · Computer Science 2026-01-29 Harsh Chaudhari , Ethan Rathbun , Hanna Foerster , Jamie Hayes , Matthew Jagielski , Milad Nasr , Ilia Shumailov , Alina Oprea

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems.…

Computation and Language · Computer Science 2023-03-28 Xukun Zhou , Jiwei Li , Tianwei Zhang , Lingjuan Lyu , Muqiao Yang , Jun He

\textbf{P}re-\textbf{T}rained \textbf{M}odel\textbf{s} have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be maliciously poisoned with certain triggers. When the triggers are…

Cryptography and Security · Computer Science 2021-09-01 Linyang Li , Demin Song , Xiaonan Li , Jiehang Zeng , Ruotian Ma , Xipeng Qiu

Web-use agents are rapidly being deployed to automate complex web tasks with extensive browser capabilities. However, these capabilities create a critical and previously unexplored attack surface. This paper demonstrates how attackers can…

Cryptography and Security · Computer Science 2025-10-22 Avishag Shapira , Parth Atulbhai Gandhi , Edan Habler , Asaf Shabtai

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key…

Cryptography and Security · Computer Science 2026-02-04 Blake Bullwinkel , Giorgio Severi , Keegan Hines , Amanda Minnich , Ram Shankar Siva Kumar , Yonatan Zunger

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Cryptography and Security · Computer Science 2025-12-05 Bingyin Zhao , Yingjie Lao

As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…

Artificial Intelligence · Computer Science 2026-02-09 Yichen Wu , Qianqian Gao , Xudong Pan , Geng Hong , Min Yang

Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…

Cryptography and Security · Computer Science 2025-11-21 Badrinath Ramakrishnan , Akshaya Balaji
‹ Prev 1 8 9 10 Next ›