AI Threat AlertBenchmarkMEDIUM
Trust The Typical
Debargha Ganguly, Sreehari Sankar, Biyao Zhang +8 more
Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We...
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 2821–2840 of 4,319 papers
DefenseMEDIUM
RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
Jiacheng Liang, Yuhui Wang, Tanqiu Jiang +1 more
Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable...
AttackHIGH
Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring
Joachim Schaeffer, Arjun Khandelwal, Tyler Tracy
Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting...
AttackHIGH
When and Where to Attack? Stage-wise Attention-Guided Adversarial Attack on Large Vision Language Models
Jaehyun Kwak, Nam Cao, Boryeong Cho +3 more
Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent...
ToolMEDIUM
PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM
Gautam Savaliya, Robert Aufschläger, Abhishek Subedi +2 more
Artificial intelligence systems introduce complex privacy risks throughout their lifecycle, especially when processing sensitive or high-dimensional...
AttackHIGH
How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks
Yanshu Wang, Shuaishuai Yang, Jingjing He +1 more
Large Language Models (LLMs) face increasing threats from jailbreak attacks that bypass safety alignment. While prompt-based defenses such as...
AttackMEDIUM
Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
Youngji Roh, Hyunjin Cho, Jaehyung Kim
Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a...
AttackMEDIUM
RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
Zeming Wei, Qiaosheng Zhang, Xia Hu +1 more
Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to...
DefenseMEDIUM
Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
Guang Yang, Xing Hu, Xiang Chen +1 more
Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design, yet remain vulnerable to backdoor attacks where...
AttackHIGH
I Can't Believe It's Not a Valid Exploit
Derin Gezgin, Amartya Das, Shinhae Kim +3 more
Recently Large Language Models (LLMs) have been used in security vulnerability detection tasks including generating proof-of-concept (PoC) exploits....
AttackHIGH
Evaluating the Vulnerability Landscape of LLM-Generated Smart Contracts
Hoang Long Do, Nasrin Sohrabi, Muneeb Ul Hassan
Large language models (LLMs) have been widely adopted in modern software development lifecycles, where they are increasingly used to automate and...
AttackHIGH
When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making
Shutong Fan, Lan Zhang, Xiaoyong Yuan
Most adversarial threats in artificial intelligence target the computational behavior of models rather than the humans who rely on them. Yet modern...
BenchmarkLOW
Privacy utility trade offs for parameter estimation in degree heterogeneous higher order networks
Bibhabasu Mandal, Sagnik Nandy
In sensitive applications involving relational datasets, protecting information about individual links from adversarial queries is of paramount...
AttackHIGH
WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
Xilong Wang, Yinuo Liu, Zhun Wang +2 more
Prompt injection attacks manipulate webpage content to cause web agents to execute attacker-specified tasks instead of the user's intended ones....
AttackMEDIUM
Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoning
Andrew Draganov, Tolga H. Dur, Anandmayi Bhongade +1 more
We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an...
AttackHIGH
Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
Chen Xiong, Zhiyuan He, Pin-Yu Chen +2 more
Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying...
BenchmarkMEDIUM
SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models
Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh +2 more
Safety alignment in Language Models (LMs) is fundamental for trustworthy AI. However, while different stakeholders are trying to leverage Arabic...
AttackHIGH
Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
Mengxuan Wang, Yuxin Chen, Gang Xu +3 more
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable...
ToolLOW
LogicScan: An LLM-driven Framework for Detecting Business Logic Vulnerabilities in Smart Contracts
Jiaqi Gao, Zijian Zhang, Yuqiang Sun +5 more
Business logic vulnerabilities have become one of the most damaging yet least understood classes of smart contract vulnerabilities. Unlike...
AttackHIGH
Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models
Hicham Eddoubi, Umar Faruk Abdullahi, Fadi Hassan
Large Language Models (LLMs) have seen widespread adoption across multiple domains, creating an urgent need for robust safety alignment mechanisms....
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