2,560+ academic papers on AI security, attacks, and defenses
Showing 141–160 of 442 papers
Clear filtersZachary Coalson, Bo Fang, Sanghyun Hong
Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in...
Gelei Deng, Yi Liu, Yuekang Li +5 more
LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28...
Simon Lermen, Daniel Paleka, Joshua Swanson +3 more
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News...
Michael Cunningham
We present a practical system for privacy-aware large language model (LLM) inference that splits a transformer between a trusted local GPU and an...
Nivya Talokar, Ayush K Tarun, Murari Mandal +2 more
LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to...
Johannes Bertram, Jonas Geiping
We introduce NESSiE, the NEceSsary SafEty benchmark for large language models (LLMs). With minimal test cases of information and access security,...
Shahriar Golchin, Marc Wetter
We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice. In isolation, we...
Haodong Zhao, Jinming Hu, Gongshen Liu
Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt...
Max Fomin
Detecting prompt injection and jailbreak attacks is critical for deploying LLM-based agents safely. As agents increasingly process untrusted data...
Mohamed Shaaban, Mohamed Elmahallawy
Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for...
Anudeep Das, Prach Chantasantitam, Gurjot Singh +3 more
Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences,...
Xu Li, Simon Yu, Minzhou Pan +5 more
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This...
Tailia Malloy, Tegawende F. Bissyande
Large Language Models are expanding beyond being a tool humans use and into independent agents that can observe an environment, reason about...
Nataša Krčo, Zexi Yao, Matthieu Meeus +1 more
Data containing personal information is increasingly used to train, fine-tune, or query Large Language Models (LLMs). Text is typically scrubbed of...
Faouzi El Yagoubi, Ranwa Al Mallah, Godwin Badu-Marfo
Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks,...
Aashish Kolluri, Rishi Sharma, Manuel Costa +5 more
Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such...
Arpit Singh Gautam, Kailash Talreja, Saurabh Jha
Large Language Models (LLMs) frequently hallucinate plausible but incorrect assertions, a vulnerability often missed by uncertainty metrics when...
Zhenhua Zou, Sheng Guo, Qiuyang Zhan +6 more
The evolution of Large Language Models (LLMs) has shifted mobile computing from App-centric interactions to system-level autonomous agents. Current...
Xinguo Feng, Zhongkui Ma, Zihan Wang +2 more
Training and fine-tuning large-scale language models largely benefit from collaborative learning, but the approach has been proven vulnerable to...
Matteo Migliarini, Berat Ercevik, Oluwagbemike Olowe +5 more
Large Language Models (LLMs) are increasingly deployed as active participants on public social media platforms, yet their behavior in these...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert