AI Threat AlertDefenseMEDIUM
Self-Mined Hardness for Safety Fine-Tuning
Prakhar Gupta, Garv Shah, Donghua Zhang
Safety fine-tuning of language models typically requires a curated adversarial dataset. We take a different approach: score each candidate prompt's...
AI Security Research
AI Threat Alert indexes 4,319+ 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
- Total4,319
- Attack1,676
- Benchmark1,229
- Defense610
- Tool432
- Survey252
Showing 281–300 of 610 papers
Clear filtersDefenseLOW
Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models
Sandra Arcos-Holzinger, Sarah M. Erfani, James Bailey +1 more
Self-supervised speech models (S3Ms) achieve strong downstream performance, yet their learned representations remain poorly understood under natural...
DefenseMEDIUM
RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
Sadia Asif, Mohammad Mohammadi Amiri
Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable...
DefenseMEDIUM
VOW: Verifiable and Oblivious Watermark Detection for Large Language Models
Xiaokun Luan, Yihao Zhang, Pengcheng Su +2 more
Large Language Model (LLM) watermarking is crucial for establishing the provenance of machine-generated text, but most existing methods rely on a...
DefenseHIGH
Learning Generalizable Multimodal Representations for Software Vulnerability Detection
Zeming Dong, Yuejun Guo, Qiang Hu +5 more
Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capture...
DefenseLOW
Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents
Eranga Bandara, Ross Gore, Asanga Gunaratna +12 more
The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance...
DefenseHIGH
PLMGH: What Matters in PLM-GNN Hybrids for Code Classification and Vulnerability Detection
Mohamed Taoufik Kaouthar El Idrissi, Edward Zulkoski, Mohammad Hamdaqa
Code understanding models increasingly rely on pretrained language models (PLMs) and graph neural networks (GNNs), which capture complementary...
DefenseMEDIUM
One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations
Ravikumar Balakrishnan, Sanket Mendapara
Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power...
DefenseMEDIUM
Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models
Nay Myat Min, Long H. Pham, Jun Sun
Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant...
DefenseMEDIUM
Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing
Kaisheng Fan, Weizhe Zhang, Yishu Gao +2 more
Defending against backdoor attacks in large language models remains a critical practical challenge. Existing defenses mitigate these threats but...
DefenseLOW
Disagreement as Signals: Dual-view Calibration for Sequential Recommendation Denoising
Sijia Li, Min Gao, Zongwei Wang +3 more
Sequential recommendation seeks to model the evolution of user interests by capturing temporal user intent and item-level transition patterns....
DefenseHIGH
Strategic Heterogeneous Multi-Agent Architecture for Cost-Effective Code Vulnerability Detection
Zhaohui Geoffrey Wang
Automated code vulnerability detection is critical for software security, yet existing approaches face a fundamental trade-off between detection...
DefenseMEDIUM
Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs
Krishiv Agarwal, Ramneet Kaur, Colin Samplawski +6 more
Effective safety auditing of large language models (LLMs) demands tools that go beyond black-box probing and systematically uncover vulnerabilities...
DefenseMEDIUM
SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs
Chao Pan, Yu Wu, Xin Yao
Internal Safety Collapse (ISC) is a failure mode in which frontier LLMs, when executing legitimate professional tasks whose correct completion...
DefenseHIGH
Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning
Ronghao Ni, Mihai Christodorescu, Limin Jia
The rapidly evolving Node$.$js ecosystem currently includes millions of packages and is a critical part of modern software supply chains, making...
DefenseMEDIUM
Evaluating LLM-Generated Obfuscated XSS Payloads for Machine Learning-Based Detection
Divyesh Gabbireddy, Suman Saha
Cross-site scripting (XSS) remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious...
DefenseMEDIUM
Malicious ML Model Detection by Learning Dynamic Behaviors
Sarang Nambiar, Dhruv Pradhan, Ezekiel Soremekun
Pre-trained machine learning models (PTMs) are commonly provided via Model Hubs (e.g., Hugging Face) in standard formats like Pickles to facilitate...
DefenseMEDIUM
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
Kun Wang, Cheng Qian, Miao Yu +6 more
Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is...
DefenseMEDIUM
Mechanistic Anomaly Detection via Functional Attribution
Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani
We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was...
DefenseMEDIUM
Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs
Ziyang Liu
Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return schemes such...
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 4,319+ 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