English
Related papers

Related papers: XOXO: Stealthy Cross-Origin Context Poisoning Atta…

200 papers

Backdoor attacks create significant security threats to language models by embedding hidden triggers that manipulate model behavior during inference, presenting critical risks for AI systems deployed in healthcare and other sensitive…

Cryptography and Security · Computer Science 2026-04-30 Mohamed Afane , Abhishek Satyam , Ke Chen , Tao Li , Junaid Farooq , Juntao Chen

Large language models (LLMs) have become ubiquitous, interfacing with humans in numerous safety-critical applications. This necessitates improving capabilities, but importantly coupled with greater safety measures to align these models with…

Computation and Language · Computer Science 2025-06-26 Ujwal Narayan , Shreyas Chaudhari , Ashwin Kalyan , Tanmay Rajpurohit , Karthik Narasimhan , Ameet Deshpande , Vishvak Murahari

Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autonomously execute complex tasks. This tight integration,…

Cryptography and Security · Computer Science 2025-09-22 Xinpeng Liu , Junming Liu , Peiyu Liu , Han Zheng , Qinying Wang , Mathias Payer , Shouling Ji , Wenhai Wang

Despite the impressive performance of Large Language Models (LLMs) in software development activities, recent studies show the concern of introducing vulnerabilities into software codebase by AI programming assistants (e.g., Copilot,…

Software Engineering · Computer Science 2024-05-08 Sung Yong Kim , Zhiyu Fan , Yannic Noller , Abhik Roychoudhury

In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted…

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

GenAI-based coding assistants have disrupted software development. The next generation of these tools is agent-based, operating with more autonomy and potentially without human oversight. Like human developers, AI agents require contextual…

Software Engineering · Computer Science 2026-02-09 Seyedmoein Mohsenimofidi , Matthias Galster , Christoph Treude , Sebastian Baltes

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…

Computation and Language · Computer Science 2024-10-10 Shuai Zhao , Meihuizi Jia , Luu Anh Tuan , Fengjun Pan , Jinming Wen

Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous…

Neural and Evolutionary Computing · Computer Science 2026-01-27 Onkar Shelar , Travis Desell

Retrieval-Augmented Generation (RAG) systems enhance response credibility and traceability by displaying reference contexts, but this transparency simultaneously introduces a novel black-box attack vector. Existing document poisoning…

Computation and Language · Computer Science 2026-01-27 Runqi Sui

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results…

Artificial Intelligence · Computer Science 2026-03-19 Yuntong Zhang , Sungmin Kang , Ruijie Meng , Marcel Böhme , Abhik Roychoudhury

While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus on text-image interplay, treating the visual modality as a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Yuan Xiong , Ziqi Miao , Lijun Li , Chen Qian , Jie Li , Jing Shao

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…

Computation and Language · Computer Science 2025-04-22 Zhengxian Wu , Juan Wen , Wanli Peng , Ziwei Zhang , Yinghan Zhou , Yiming Xue

Agentic AI coding assistants can edit files, run commands, and access the internet on behalf of developers. However, their reliance on unvetted external artifacts introduces a new attack vector. Hidden instructions in external artifacts can…

Software Engineering · Computer Science 2026-05-26 Yue Liu , Yanjie Zhao , Yunbo Lyu , Ting Zhang , Haoyu Wang , David Lo

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due…

Cryptography and Security · Computer Science 2025-08-22 Zhiqiang Wang , Yichao Gao , Yanting Wang , Suyuan Liu , Haifeng Sun , Haoran Cheng , Guanquan Shi , Haohua Du , Xiangyang Li

We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment tasks. Our proposed…

Computation and Language · Computer Science 2020-12-25 Rishabh Maheshwary , Saket Maheshwary , Vikram Pudi

Large Language Models (LLMs) such as OpenAI Codex are increasingly being used as AI-based coding assistants. Understanding the impact of these tools on developers' code is paramount, especially as recent work showed that LLMs may suggest…

Cryptography and Security · Computer Science 2023-02-28 Gustavo Sandoval , Hammond Pearce , Teo Nys , Ramesh Karri , Siddharth Garg , Brendan Dolan-Gavitt

While convenient, relying on LLM-powered code assistants in day-to-day work gives rise to severe attacks. For instance, the assistant might introduce subtle flaws and suggest vulnerable code to the user. These adversarial code-suggestions…

Cryptography and Security · Computer Science 2024-10-15 Karl Rubel , Maximilian Noppel , Christian Wressnegger

The research builds and evaluates the adversarial potential to introduce copied code or hallucinated AI recommendations for malicious code in popular code repositories. While foundational large language models (LLMs) from OpenAI, Google,…

Cryptography and Security · Computer Science 2024-10-10 David Noever , Forrest McKee

The Model Context Protocol (MCP) has emerged as a universal standard that enables AI agents to seamlessly connect with external tools, significantly enhancing their functionality. However, while MCP brings notable benefits, it also…

Cryptography and Security · Computer Science 2026-05-26 Yongjian Guo , Puzhuo Liu , Wanlun Ma , Zehang Deng , Xiaogang Zhu , Peng Di , Xi Xiao , Sheng Wen

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 2024-05-21 Aftab Hussain , Md Rafiqul Islam Rabin , Mohammad Amin Alipour