2,077+ academic papers on AI security, attacks, and defenses
Showing 461–480 of 2,077 papers
Yang Liu, Armstrong Foundjem, Xingfang Wu +2 more
Context: In the fast-paced evolution of software development, Large Language Models (LLMs) have become indispensable tools for tasks such as code...
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...
Abhishek Saini, Haolin Jiang, Hang Liu
The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted...
J Alex Corll
Multi-turn prompt injection attacks distribute malicious intent across multiple conversation turns, exploiting the assumption that each turn is...
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...
Adel ElZemity, Joshua Sylvester, Budi Arief +1 more
SMS-based phishing (smishing) attacks have surged, yet training effective on-device detectors requires labelled threat data that quickly becomes...
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...
Samal Mukhtar, Yinghua Yao, Zhu Sun +3 more
Software vulnerability detection (SVD) is a critical challenge in modern systems. Large language models (LLMs) offer natural-language explanations...
Enrico Ahlers, Daniel Passon, Yannic Noller +1 more
Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to...
Yuxin Cao, Wei Song, Shangzhi Xu +2 more
Video Large Language Models (VideoLLMs) have recently achieved strong performance in video understanding tasks. However, we identify a previously...
Shuyu Chang, Haiping Huang, Yanjun Zhang +3 more
Code models are increasingly adopted in software development but remain vulnerable to backdoor attacks via poisoned training data. Existing backdoor...
Zhibin Duan, Guowei Rong, Zhuo Li +3 more
Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedback, yet...
Zijing Xu, Ziwei Ning, Tiancheng Hu +4 more
The rapid evolution of cyber threats has highlighted significant gaps in security knowledge integration. Cybersecurity Knowledge Graphs (CKGs)...
Qianli Wang, Boyang Ma, Minghui Xu +1 more
LLM agents often rely on Skills to describe available tools and recommended procedures. We study a hidden-comment prompt injection risk in this...
Viet Hoang Luu, Amirmohammad Pasdar, Wachiraphan Charoenwet +3 more
Modern fuzzers scale to large, real-world software but often fail to exercise the program states developers consider most fragile or...
Mohan Rajagopalan, Vinay Rao
Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot...
Ashwath Vaithinathan Aravindan, Mayank Kejriwal
Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the...
Peiran Wang, Xinfeng Li, Chong Xiang +5 more
The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against...
Yilin Yang, Zhenghui Guo, Yuke Wang +3 more
Large Vision-Language Models (VLMs) have achieved remarkable success across diverse multimodal tasks but remain vulnerable to hallucinations rooted...
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