2,589+ academic papers on AI security, attacks, and defenses
Showing 1441–1460 of 2,589 papers
Zhiyuan Chang, Mingyang Li, Yuekai Huang +6 more
Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt...
Hoagy Cunningham, Jerry Wei, Zihan Wang +26 more
We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and...
Saad Alqithami
Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step...
Yunhao Feng, Yige Li, Yutao Wu +6 more
Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables...
Mohamed Nabeel, Oleksii Starov
According to Gartner, more than 70% of organizations will have integrated AI models into their workflows by the end of 2025. In order to reduce cost...
Sahaya Jestus Lazer, Kshitiz Aryal, Maanak Gupta +1 more
Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over...
Jacob Ede Levine, Yun Lyan Luo, Sai Chandra Kosaraju
The design of reliable, valid, and diverse molecules is fundamental to modern drug discovery, as improved molecular generation supports efficient...
Atharv Naphade
Retrieval-Augmented Generation (RAG) is the prevailing paradigm for grounding Large Language Models (LLMs), yet the mechanisms governing how models...
San Kim, Gary Geunbae Lee
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad...
Ahmad Mohammad Saber, Saeed Jafari, Zhengmao Ouyang +3 more
This paper presents a large language model (LLM)-based framework that adapts and fine-tunes compact LLMs for detecting cyberattacks on transformer...
Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis +2 more
Current safety evaluations of large language models (LLMs) create a dangerous illusion of universality, aggregating "Identity Hate" into scalar...
Yu Yan, Sheng Sun, Mingfeng Li +6 more
Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and...
Xinyue Lou, Jinan Xu, Jingyi Yin +8 more
As Multimodal Large Language Models (MLLMs) become an indispensable assistant in human life, the unsafe content generated by MLLMs poses a danger to...
Siyuan Li, Xi Lin, Jun Wu +5 more
Jailbreak attacks pose significant threats to large language models (LLMs), enabling attackers to bypass safeguards. However, existing reactive...
Andreea-Elena Bodea, Stephen Meisenbacher, Alexandra Klymenko +1 more
The continued promise of Large Language Models (LLMs), particularly in their natural language understanding and generation capabilities, has driven a...
Haeun Jang, Hwan Chang, Hwanhee Lee
The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined...
Xiaoyu Xu, Minxin Du, Zitong Li +6 more
Although machine unlearning is essential for removing private, harmful, or copyrighted content from LLMs, current benchmarks often fail to faithfully...
Xing Li, Hui-Ling Zhen, Lihao Yin +3 more
This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and...
Dinesh Srivasthav P, Ashok Urlana, Rahul Mishra +2 more
Machine unlearning aims to selectively remove the influence of specific training samples to satisfy privacy regulations such as the GDPR's 'Right to...
Jin Wang, Liang Lin, Kaiwen Luo +8 more
While Audio Large Language Models (ALLMs) have achieved remarkable progress in understanding and generation, their potential privacy implications...
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