Monthly publications
Paper types
attack 20
defense 2
benchmark 1
Domains
nlp 23
vision 3
multimodal 3
reinforcement-learning 1
Co-occurring categories
Other OWASP categories that appear on the same papers
Top cited papers
172433425161718090100
ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking
2025 attack
LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation
2025 attack
Sponge Tool Attack: Stealthy Denial-of-Efficiency against Tool-Augmented Agentic Reasoning
2026 attack
Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
2026 attack
One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
2025 attack
BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
2025 attack
Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark
2025 benchmark
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
2025 attack
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
2026 defense
Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model
2026 attack