AI Threat Alert
Attack HIGH
Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems
Zhaojiacheng Zhou
Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills...
AI Security Research
AI Threat Alert indexes 3,092+ 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
- Total3,092
- Attack1,201
- Benchmark886
- Defense422
- Tool322
- Survey181
Showing 541–560 of 3,092 papers
Attack HIGH
IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
Chia-Pei, Chen, Kentaroh Toyoda +2 more
Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still...
Survey MEDIUM
Behavioral Integrity Verification for AI Agent Skills
Yuhao Wu, Tung-Ling Li, Hongliang Liu
Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution....
Attack HIGH
Persona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation
Cristian Morasso, Anisa Halimi, Muhammad Zaid Hameed +1 more
Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety...
Defense MEDIUM
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models
Xinyi Zeng, Xue Yang, Jingyuan Zhang +5 more
Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant...
Attack HIGH
Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
Zeguan Xiao, Xuanzhe Xu, Yun Chen +4 more
Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy,...
Attack HIGH
When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
Ziyu Liu, Tao Li, Tianjie Ni +5 more
Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token...
Survey LOW
SoK: Unlearnability and Unlearning for Model Dememorization
Mengying Zhang, Derui Wang, Ruoxi Sun +3 more
Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards...
Benchmark LOW
When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
Fanpu Cao, Xin Zou, Xuming Hu +1 more
Multimodal large language models (MLLMs) have become a key interface for visual reasoning and grounded question answering, yet they remain vulnerable...
Attack MEDIUM
Agents Should Replace Narrow Predictive AI as the Orchestrator in 6G AI-RAN
Pranshav Gajjar, Vijay K Shah
This position paper argues that to achieve Level 5 autonomous 6G networks, the next generation of Artificial Intelligence in Radio Access Networks...
Tool MEDIUM
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
Fanxiao Li, Jiaying Wu, Tingchao Fu +3 more
Multi-agent systems (MAS) powered by large language models (LLMs) increasingly adopt planner--executor architectures, where planners convert prompts...
Tool MEDIUM
NeuroFlake: A Neuro-Symbolic LLM Framework for Flaky Test Classification
Khondaker Tasnia Hoque, Toukir Ahammed
Flaky tests, which exhibit non-deterministic pass/fail behavior for the same version of code, pose significant challenges to reliable regression...
Attack HIGH
Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection
Zi Liang, Ronghua Li, Yanyun Wang +2 more
Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of...
Other LOW
Natural Language based Specification and Verification
Zhaorui Li, Chengyu Song
Recent frontier large language models (LLMs) have shown strong performance in identifying security vulnerabilities in large, mature open-source...
Attack HIGH
Context-Aware Spear Phishing: Generative AI-Enabled Attacks Against Individuals via Public Social Media Data
Elham Pourabbas Vafa, Sayak Saha Roy, Shirin Nilizadeh
We demonstrate how publicly available social-media data and generative AI (GenAI) can be misused to automate and scale highly personalized,...
Defense MEDIUM
Leveraging RAG for Training-Free Alignment of LLMs
John T. Halloran
Large language model (LLM) alignment algorithms typically consist of post-training over preference pairs. While such algorithms are widely used to...
Attack HIGH
Adversarial SQL Injection Generation with LLM-Based Architectures
Ali Karakoc, H. Birkan Yilmaz
SQL injection (SQLi) attacks are still one of the serious attacks ranked in the Open Worldwide Application Security Project (OWASP) Top 10 threats....
Benchmark LOW
Benchmarking LLM-Based Static Analysis for Secure Smart Contract Development: Reliability, Limitations, and Potential Hybrid Solutions
Stefan-Claudiu Susan, Andrei Arusoaie, Dorel Lucanu
The irreversible nature of blockchain transactions makes the identification of smart contract vulnerabilities an essential requirement for secure...
Defense MEDIUM
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
Christian Moya, Alex Semendinger, Guang Lin +1 more
Preference learning methods such as Direct Preference Optimization (DPO) are known to induce reliance on spurious correlations, leading to sycophancy...
Defense MEDIUM
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
Fatima Z. Abacha, Sin G. Teo, Yuanxiang Wu +2 more
Federated Learning remains highly susceptible to backdoor attacks--malicious clients inject targeted behaviours into the global model. Existing...
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 3,092+ 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