AI Threat Alert indexes 3,023+ peer-reviewed and preprint papers on AI/ML security — covering adversarial attacks, model defenses, red-teaming benchmarks, surveys, and security tooling. Papers are sourced from arXiv, classified by type and by relevance to real-world threats, and cross-referenced with the CVEs and incidents they relate to.
Showing 221–240 of 1,175 papers
Clear filtersMd Farhamdur Reza, Richeng Jin, Tianfu Wu +1 more
Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to...
Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim +5 more
Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models,...
Samuel Korn
Retrieval-Augmented Generation (RAG) systems are vulnerable to knowledge base poisoning, yet existing attacks have been evaluated almost exclusively...
Yiwei Zhang, Jeremiah Birrell, Reza Ebrahimi +3 more
Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors...
Marco Rando, Samuel Vaiter
Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit...
Zheng Fang, Xiaosen Wang, Shenyi Zhang +2 more
Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire...
Jan Dolejš, Martin Jureček, Róbert Lórencz
Modern malware detection pipelines rely on continuous data ingestion and machine learning to counter the high volume of novel threats. This work...
Zekun Fei, Zihao Wang, Weijie Liu +4 more
Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based...
Jie Zhang, Pura Peetathawatchai, Florian Tramèr +1 more
Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and...
Sarthak Choudhary, Atharv Singh Patlan, Nils Palumbo +3 more
We present Sparse Backdoor, a supply-chain attack that plants a \emph{provably undetectable} backdoor in pre-trained image classifiers, including...
Raja Sekhar Rao Dheekonda, Will Pearce, Nick Landers
AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is...
Shravya Kanchi, Xiaoyan Zang, Ying Zhang +2 more
Developers create modern software applications (Apps) on top of third-party libraries (Libs). When library vulnerabilities are reachable through...
Gabriel Hortea, Juan Tapiador
Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based...
Gabriel Hortea, Juan Tapiador
Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based...
Tejas Kulkarni, Antti Koskela, Laith Zumot
We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be...
Ishrith Gowda
Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We...
Shihao Weng, Yang Feng, Jinrui Zhang +3 more
The rise of Large Language Model (LLM) agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among...
Divyam Anshumaan, Sarthak Choudhary, Nils Palumbo +1 more
LLM agents release private data across multi-service interactions. Existing prompt sanitizers based on metric differential privacy treat each release...
Mingshuo Liu, Yiwei Zha, Min Chen
Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style...
Kemal Derya, Berk Sunar
Defending large language models (LLMs) against jailbreak attacks, such as Greedy Coordinate Gradient (GCG), remains a challenge, particularly under...
AI security research studies how AI and machine-learning systems can be attacked and defended — covering adversarial examples, prompt injection, model poisoning, training-data extraction, and the mitigations against them. AI Threat Alert curates this research from academic sources so security teams can track the threats behind emerging AI risks.
AI Threat Alert indexes 3,023+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Papers are sourced from arXiv, then classified by type and by relevance to real-world AI/ML threats, and cross-referenced with the CVEs and incidents they relate to.
Coverage spans adversarial attacks, model and system defenses, red-teaming benchmarks, literature surveys, and security tooling for LLMs, ML libraries, AI agents, and inference pipelines.
Every paper is filtered for AI security relevance and linked to the vulnerabilities, vendors, and incidents it relates to, so the research connects directly to operational threat intelligence.
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