AI Threat Alert
Benchmark LOW
RESCUE: Retrieval Augmented Secure Code Generation
Jiahao Shi, Tianyi Zhang
Despite recent advances, Large Language Models (LLMs) still generate vulnerable code. Retrieval-Augmented Generation (RAG) has the potential to...
AI Security Research
AI Threat Alert indexes 3,771+ 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.
- Adversarial attacks
- Model defenses
- Red-teaming benchmarks
- Surveys
- Security tooling
- Total3,771
- Attack1,458
- Benchmark1,072
- Defense533
- Tool380
- Survey220
Showing 3381–3400 of 3,771 papers
Benchmark HIGH
Black-Box Evasion Attacks on Data-Driven Open RAN Apps: Tailored Design and Experimental Evaluation
Pranshav Gajjar, Molham Khoja, Abiodun Ganiyu +4 more
The impending adoption of Open Radio Access Network (O-RAN) is fueling innovation in the RAN towards data-driven operation. Unlike traditional RAN...
Benchmark HIGH
BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
Chengquan Guo, Yuzhou Nie, Chulin Xie +3 more
As large language models (LLMs) are increasingly used for code generation, concerns over the security risks have grown substantially. Early research...
Attack HIGH
CourtGuard: A Local, Multiagent Prompt Injection Classifier
Isaac Wu, Michael Maslowski
As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful...
Defense LOW
SAVANT: Semantic Analysis with Vision-Augmented Anomaly deTection
Roberto Brusnicki, David Pop, Yuan Gao +2 more
Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution scenarios with semantic anomalies. While Vision...
Attack HIGH
PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits
Neeladri Bhuiya, Madhav Aggarwal, Diptanshu Purwar
Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de facto...
Tool HIGH
VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
Qilin Liao, Anamika Lochab, Ruqi Zhang
Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored...
Attack HIGH
CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
Xu Zhang, Hao Li, Zhichao Lu
Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks....
Attack HIGH
GUIDE: Enhancing Gradient Inversion Attacks in Federated Learning with Denoising Models
Vincenzo Carletti, Pasquale Foggia, Carlo Mazzocca +2 more
Federated Learning (FL) enables collaborative training of Machine Learning (ML) models across multiple clients while preserving their privacy. Rather...
Attack MEDIUM
Agentic Reinforcement Learning for Search is Unsafe
Yushi Yang, Shreyansh Padarha, Andrew Lee +1 more
Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common...
Attack HIGH
PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
Xinkai Wang, Beibei Li, Zerui Shao +3 more
Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual...
Tool MEDIUM
Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems
Rishi Jha, Harold Triedman, Justin Wagle +1 more
Control-flow hijacking attacks manipulate orchestration mechanisms in multi-agent systems into performing unsafe actions that compromise the system...
Attack HIGH
Exploiting the Potential of Linearity in Automatic Differentiation and Computational Cryptography
Giulia Giusti
The concept of linearity plays a central role in both mathematics and computer science, with distinct yet complementary meanings. In mathematics,...
Defense MEDIUM
Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
Runlin Lei, Lu Yi, Mingguo He +4 more
While Graph Neural Networks (GNNs) and Large Language Models (LLMs) are powerful approaches for learning on Text-Attributed Graphs (TAGs), a...
Defense HIGH
ParaVul: A Parallel Large Language Model and Retrieval-Augmented Framework for Smart Contract Vulnerability Detection
Tenghui Huang, Jinbo Wen, Jiawen Kang +8 more
Smart contracts play a significant role in automating blockchain services. Nevertheless, vulnerabilities in smart contracts pose serious threats to...
Attack MEDIUM
Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models
Elias Hossain, Swayamjit Saha, Somshubhra Roy +1 more
Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference...
Defense MEDIUM
SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents
Qiusi Zhan, Angeline Budiman-Chan, Abdelrahman Zayed +3 more
Large language model (LLM) based search agents iteratively generate queries, retrieve external information, and reason to answer open-domain...
Defense MEDIUM
SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents
Qiusi Zhan, Angeline Budiman-Chan, Abdelrahman Zayed +3 more
Large language model (LLM) based search agents iteratively generate queries, retrieve external information, and reason to answer open-domain...
Attack HIGH
Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization
Masahiro Kaneko, Zeerak Talat, Timothy Baldwin
Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the...
Attack HIGH
Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
Masahiro Kaneko, Timothy Baldwin
Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property...
Frequently asked questions
What is AI security research?
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.
How many AI security papers does AI Threat Alert track?
AI Threat Alert indexes 3,771+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Where do the research papers come from?
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.
What topics does the AI security research cover?
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.
How is this different from a generic paper search?
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.
Track AI security vulnerabilities in real time
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