AI Threat Alert
Benchmark MEDIUM
Parallax: Why AI Agents That Think Must Never Act
Joel Fokou
Autonomous AI agents are rapidly transitioning from experimental tools to operational infrastructure, with projections that 80% of enterprise...
AI Security Research
AI Threat Alert indexes 3,406+ 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
- Total3,406
- Attack1,315
- Benchmark981
- Defense479
- Tool341
- Survey196
Showing 601–620 of 1,673 papers
Clear filters Attack MEDIUM
Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory
Shaopeng Fu, Di Wang
Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To...
Attack MEDIUM
Robust Semi-Supervised Temporal Intrusion Detection for Adversarial Cloud Networks
Anasuya Chattopadhyay, Daniel Reti, Hans D. Schotten
Cloud networks increasingly rely on machine learning based Network Intrusion Detection Systems to defend against evolving cyber threats. However,...
Attack MEDIUM
LLM-Guided Prompt Evolution for Password Guessing
Vladimir A. Mazin, Mikhail A. Zorin, Dmitrii S. Korzh +3 more
Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale...
Benchmark MEDIUM
VeriX-Anon: A Multi-Layered Framework for Mathematically Verifiable Outsourced Target-Driven Data Anonymization
Miit Daga, Swarna Priya Ramu
Organisations increasingly outsource privacy-sensitive data transformations to cloud providers, yet no practical mechanism lets the data owner verify...
Benchmark MEDIUM
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Rui Yin, Tianxu Han, Naen Xu +8 more
Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain...
Benchmark MEDIUM
From IOCs to Regex: Automating CTI Operationalization for SOC with LLMs
Pei-Yu Tseng, Lan Zhang, ZihDwo Yeh +3 more
Cyber Threat Intelligence (CTI) reports contain Indicators of Compromise (IOCs) that are critical for security operations. To operationalize these...
Tool MEDIUM
TimeMark: A Trustworthy Time Watermarking Framework for Exact Generation-Time Recovery from AIGC
Shangkun Che, Silin Du, Ge Gao
The widespread use of Large Language Models (LLMs) in text generation has raised increasing concerns about intellectual property disputes....
Attack MEDIUM
AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
Hongru Song, Yu-An Liu, Ruqing Zhang +4 more
Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack...
Attack MEDIUM
Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference
Anes Abdennebi, Nadjia Kara, Laaziz Lahlou
The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance,...
Defense MEDIUM
Towards Platonic Representation for Table Reasoning: A Foundation for Permutation-Invariant Retrieval
Willy Carlos Tchuitcheu, Tan Lu, Ann Dooms
Historical approaches to Table Representation Learning (TRL) have largely adopted the sequential paradigms of Natural Language Processing (NLP). We...
Defense MEDIUM
Detecting Safety Violations Across Many Agent Traces
Adam Stein, Davis Brown, Hamed Hassani +2 more
To identify safety violations, auditors often search over large sets of agent traces. This search is difficult because failures are often rare,...
Benchmark MEDIUM
Towards Automated Pentesting with Large Language Models
Ricardo Bessa, Rui Claro, João Trindade +1 more
Large Language Models (LLMs) are redefining offensive cybersecurity by allowing the generation of harmful machine code with minimal human...
Defense MEDIUM
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
Junxiao Yang, Haoran Liu, Jinzhe Tu +9 more
Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried...
Benchmark MEDIUM
RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
Hanbo Huang, Xuan Gong, Yiran Zhang +2 more
Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to...
Benchmark MEDIUM
RedShell: A Generative AI-Based Approach to Ethical Hacking
Ricardo Bessa, Rui Claro, João Trindade +1 more
The application of Machine Learning techniques in code generation is now a common practice for most developers. Tools such as ChatGPT from OpenAI...
Other MEDIUM
CLASP: Closed-loop Asynchronous Spatial Perception for Open-vocabulary Desktop Object Grasping
Yiran Ling, Wenxuan Li, Siying Dong +5 more
Robot grasping of desktop object is widely used in intelligent manufacturing, logistics, and agriculture.Although vision-language models (VLMs) show...
Attack MEDIUM
Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models
Shuhao Zhang, Yuli Chen, Jiale Han +2 more
Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text....
Benchmark MEDIUM
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
Xiaomeng Hu, Yinger Zhang, Fei Huang +7 more
AI agents are expected to perform professional work across hundreds of occupational domains (from emergency department triage to nuclear reactor...
Benchmark MEDIUM
DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
Yuchen Chen, Yuan Xiao, Chunrong Fang +2 more
The proliferation of large language models for code (CodeLMs) and open-source contributions has heightened concerns over unauthorized use of source...
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 3,406+ 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