AI Threat Alert
Benchmark MEDIUM
Watermarks for Embeddings-as-a-Service Large Language Models
Anudeex Shetty
Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs,...
AI Security Research
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.
- Adversarial attacks
- Model defenses
- Red-teaming benchmarks
- Surveys
- Security tooling
- Total3,023
- Attack1,175
- Benchmark866
- Defense407
- Tool319
- Survey176
Showing 641–660 of 866 papers
Clear filters Benchmark MEDIUM
Ghosting Your LLM: Without The Knowledge of Your Gradient and Data
Abeer Matar A. Almalky, Ziyan Wang, Mohaiminul Al Nahian +2 more
In recent years, large language models (LLMs) have achieved substantial advancements and are increasingly integrated into critical applications...
Benchmark MEDIUM
CacheTrap: Injecting Trojans in LLMs without Leaving any Traces in Inputs or Weights
Mohaiminul Al Nahian, Abeer Matar A. Almalky, Gamana Aragonda +6 more
Adversarial weight perturbation has emerged as a concerning threat to LLMs that either use training privileges or system-level access to inject...
Benchmark MEDIUM
Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
Gauri Pradhan, Joonas Jälkö, Santiago Zanella-Bèguelin +1 more
Training machine learning models with differential privacy (DP) limits an adversary's ability to infer sensitive information about the training data....
Benchmark LOW
MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning
Junjian Wang, Lidan Zhao, Xi Sheryl Zhang
Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where...
Benchmark MEDIUM
Constructing and Benchmarking: a Labeled Email Dataset for Text-Based Phishing and Spam Detection Framework
Rebeka Toth, Tamas Bisztray, Richard Dubniczky
Phishing and spam emails remain a major cybersecurity threat, with attackers increasingly leveraging Large Language Models (LLMs) to craft highly...
Benchmark MEDIUM
The Phish, The Spam, and The Valid: Generating Feature-Rich Emails for Benchmarking LLMs
Rebeka Toth, Tamas Bisztray, Nils Gruschka
In this paper, we introduce a metadata-enriched generation framework (PhishFuzzer) that seeds real emails into Large Language Models (LLMs) to...
Benchmark MEDIUM
RaX-Crash: A Resource Efficient and Explainable Small Model Pipeline with an Application to City Scale Injury Severity Prediction
Di Zhu, Chen Xie, Ziwei Wang +1 more
New York City reports over one hundred thousand motor vehicle collisions each year, creating substantial injury and public health burden. We present...
Benchmark MEDIUM
PILOT: Command-line Interface Fuzzing via Path-Guided, Iterative Large Language Model Prompting
Momoko Shiraishi, Yinzhi Cao, Takahiro Shinagawa
Command-line interface (CLI) fuzzing tests programs by mutating both command-line options and input file contents, thus enabling discovery of...
Benchmark MEDIUM
APT-CGLP: Advanced Persistent Threat Hunting via Contrastive Graph-Language Pre-Training
Xuebo Qiu, Mingqi Lv, Yimei Zhang +4 more
Provenance-based threat hunting identifies Advanced Persistent Threats (APTs) on endpoints by correlating attack patterns described in Cyber Threat...
Benchmark MEDIUM
Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?
David Amebley, Sayanton Dibbo
In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data...
Benchmark MEDIUM
DUALGUAGE: Automated Joint Security-Functionality Benchmarking for Secure Code Generation
Abhijeet Pathak, Suvadra Barua, Dinesh Gudimetla +4 more
Large language models (LLMs) and autonomous coding agents are increasingly used to generate software across a wide range of domains. Yet a core...
Benchmark MEDIUM
Synthetic Data: AI's New Weapon Against Android Malware
Angelo Gaspar Diniz Nogueira, Kayua Oleques Paim, Hendrio Bragança +2 more
The ever-increasing number of Android devices and the accelerated evolution of malware, reaching over 35 million samples by 2024, highlight the...
Benchmark MEDIUM
Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion
Yu Cui, Yifei Liu, Hang Fu +4 more
Research on the safety evaluation of large language models (LLMs) has become extensive, driven by jailbreak studies that elicit unsafe responses....
Benchmark MEDIUM
Can LLMs Recover Program Semantics? A Systematic Evaluation with Symbolic Execution
Rong Feng, Suman Saha
Obfuscation poses a persistent challenge for software engineering tasks such as program comprehension, maintenance, testing, and vulnerability...
Benchmark MEDIUM
Medical Malice: A Dataset for Context-Aware Safety in Healthcare LLMs
Andrew Maranhão Ventura D'addario
The integration of Large Language Models (LLMs) into healthcare demands a safety paradigm rooted in \textit{primum non nocere}. However, current...
Benchmark LOW
LLM-CSEC: Empirical Evaluation of Security in C/C++ Code Generated by Large Language Models
Muhammad Usman Shahid, Chuadhry Mujeeb Ahmed, Rajiv Ranjan
The security of code generated by large language models (LLMs) is a significant concern, as studies indicate that such code often contains...
Benchmark HIGH
BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
Juncheng Li, Yige Li, Hanxun Huang +5 more
Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously...
Benchmark MEDIUM
RoguePrompt: Dual-Layer Ciphering for Self-Reconstruction to Circumvent LLM Moderation
Benyamin Tafreshian
Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically...
Benchmark MEDIUM
Think Fast: Real-Time IoT Intrusion Reasoning Using IDS and LLMs at the Edge Gateway
Saeid Jamshidi, Amin Nikanjam, Negar Shahabi +4 more
As the number of connected IoT devices continues to grow, securing these systems against cyber threats remains a major challenge, especially in...
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 3,023+ 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