AI Threat Alert
Other HIGH
For Those Who May Find Themselves on the Red Team
Tyler Shoemaker
This position paper argues that literary scholars must engage with large language model (LLM) interpretability research. While doing so will involve...
AI Security Research
AI Threat Alert indexes 3,397+ 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
- Total3,397
- Attack1,314
- Benchmark975
- Defense477
- Tool341
- Survey196
Showing 881–900 of 1,146 papers
Clear filters Attack HIGH
Exploiting the Experts: Unauthorized Compression in MoE-LLMs
Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha +1 more
Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their...
Attack HIGH
Vulnerability-Aware Robust Multimodal Adversarial Training
Junrui Zhang, Xinyu Zhao, Jie Peng +3 more
Multimodal learning has shown significant superiority on various tasks by integrating multiple modalities. However, the interdependencies among...
Attack HIGH
Federated Anomaly Detection and Mitigation for EV Charging Forecasting Under Cyberattacks
Oluleke Babayomi, Dong-Seong Kim
Electric Vehicle (EV) charging infrastructure faces escalating cybersecurity threats that can severely compromise operational efficiency and grid...
Attack HIGH
Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
Yunyi Zhang, Shibo Cui, Baojun Liu +4 more
LLM applications (i.e., LLM apps) leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional...
Attack HIGH
Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models
Zhiyuan Xu, Stanislav Abaimov, Joseph Gardiner +1 more
Modern large language models (LLMs) are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an...
Benchmark HIGH
ReVul-CoT: Towards Effective Software Vulnerability Assessment with Retrieval-Augmented Generation and Chain-of-Thought Prompting
Zhijie Chen, Xiang Chen, Ziming Li +2 more
Context: Software Vulnerability Assessment (SVA) plays a vital role in evaluating and ranking vulnerabilities in software systems to ensure their...
Benchmark HIGH
The Shawshank Redemption of Embodied AI: Understanding and Benchmarking Indirect Environmental Jailbreaks
Chunyang Li, Zifeng Kang, Junwei Zhang +4 more
The adoption of Vision-Language Models (VLMs) in embodied AI agents, while being effective, brings safety concerns such as jailbreaking. Prior work...
Attack HIGH
"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
Zhen Sun, Zongmin Zhang, Deqi Liang +8 more
As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box...
Attack HIGH
Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models
Yijun Yang, Lichao Wang, Jianping Zhang +3 more
The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and...
Attack HIGH
AutoBackdoor: Automating Backdoor Attacks via LLM Agents
Yige Li, Zhe Li, Wei Zhao +4 more
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors...
Survey HIGH
Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming
Strahinja Janjusevic, Anna Baron Garcia, Sohrob Kazerounian
Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests....
Attack HIGH
What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
Zhihan Ren, Lijun He, Jiaxi Liang +3 more
Split DNNs enable edge devices by offloading intensive computation to a cloud server, but this paradigm exposes privacy vulnerabilities, as the...
Attack HIGH
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
Piercosma Bisconti, Matteo Prandi, Federico Pierucci +7 more
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25...
Attack HIGH
Securing AI Agents Against Prompt Injection Attacks
Badrinath Ramakrishnan, Akshaya Balaji
Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant...
Survey HIGH
Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks
Zimo Ji, Xunguang Wang, Zongjie Li +6 more
Large Language Model (LLM)-based agents with function-calling capabilities are increasingly deployed, but remain vulnerable to Indirect Prompt...
Benchmark HIGH
Attacking Autonomous Driving Agents with Adversarial Machine Learning: A Holistic Evaluation with the CARLA Leaderboard
Henry Wong, Clement Fung, Weiran Lin +3 more
To autonomously control vehicles, driving agents use outputs from a combination of machine-learning (ML) models, controller logic, and custom...
Attack HIGH
Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education
Xin Yi, Yue Li, Dongsheng Shi +3 more
Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning...
Attack HIGH
Sigil: Server-Enforced Watermarking in U-Shaped Split Federated Learning via Gradient Injection
Zhengchunmin Dai, Jiaxiong Tang, Peng Sun +2 more
In decentralized machine learning paradigms such as Split Federated Learning (SFL) and its variant U-shaped SFL, the server's capabilities are...
Attack HIGH
SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
Eric Xue, Ruiyi Zhang, Pengtao Xie
Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target...
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 3,397+ 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