AI Threat Alert indexes 3,371+ 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 61–80 of 236 papers
Clear filtersSungju Yun, Sijune Hwang, Yeonjoon Lee +2 more
Detecting source code vulnerabilities is increasingly difficult as modern security flaws are rooted in complex causal dependencies between execution...
Jong Wook Kim, Byoungjae Min, Kennedy Edemacu +3 more
Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected...
Haocheng Fu, Yuqi Qian, Luyao Wang +1 more
Large language model (LLM) watermarking provides an important mechanism for tracing the provenance of generated text. Existing statistical watermarks...
Yuhan You, Suhas Adavelly, Victoria Lovelace +3 more
Agentic artificial intelligence raises a new security concern: cyber threats that reason, act, and adapt locally without continuous human direction....
Yongwan Jo, Jinyoung Park, Euihyun Lee +1 more
Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens....
Walid Saidi
Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers...
Giorgio Severi, Shujaat Mirza, Blake Bullwinkel +1 more
Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning...
Yiran Gao, Tao Li, Kim Hammar
Incident response is currently managed by security operators using predefined playbooks, resulting in slow, labor-intensive security decision-making...
Supriti Vijay, Aman Priyanshu, Didier Chapoteau +8 more
Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify...
Vincenzo Longo, Alberto Verna, Nikhil Jha +1 more
The Microsoft 365 (M365) ecosystem hosts thousands of third-party applications that integrate with enterprise tenants via fine-grained OAuth...
Giovanni Pizzenti, Alberto Verna, Nikhil Jha +3 more
In recent years, cybersecurity threats have increasingly exploited human behaviour rather than purely technical vulnerabilities, exposing the limits...
Yan Huang, Guowei Wang, Xu Wang +2 more
Vision-language models (VLMs) such as CLIP exhibit remarkable zero-shot capabilities, yet their performance frequently degrades sharply under...
Xuanhui Lin, Junhao Dong, Mingrong Gong +3 more
Vision-language models (VLMs) exhibit strong generalization across multimodal tasks but remain vulnerable to adversarial perturbations. Existing...
Junyeong Park, Jieun Han, Haneul Yoo +3 more
Large language models (LLMs) are increasingly used across diverse tasks in K-12 education, yet existing safety evaluations rarely examine how harmful...
Jia-Chen Zhang, Ze-Yu Zhang, Kai-Wei Zhang
Computer-use agents (CUAs), which empower large language models to autonomously operate operating systems and the web, are increasingly vulnerable to...
Yuekun Wang, Mingfei Cheng, Xiaofei Xie
LLM-based code auditors are increasingly integrated into pull-request (PR) workflows, yet their reliability against adversarial changes distributed...
K. Jack Scott, Narun Pat, Veronica Liesaputra
In this work we investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis of three models spanning three...
Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Colton Payne +4 more
Large language models are increasingly used to reason about software vulnerabilities, but their outputs can silently violate domain knowledge,...
Bingyu Yan, Xiaoming Zhang, Chaozhuo Li +3 more
Self-evolving large language model agents improve their capabilities by distilling interaction trajectories into persistent experiences. Yet this...
Zheng Lin, Yuzhe Huang, Zhenxing Niu +2 more
Long-term memory enables LLM agents to retain useful information across sessions, but also creates an attack surface through which adversaries may...
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 3,371+ 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