iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
ControlMap: Controllable HD Map Generation Using Latent Diffusion for Traffic Simulation Akasha 2 Achieves 4x Faster Visual Synthesis with Hamiltonian-Inspired AI Architecture PURe Module Enhances Vision Networks by Adding Multiplicative Local Interactions New Unified Definition of AI Hallucination Pins It on Inaccurate World Modeling Attention, Not Model Scale, Drives Human-AI Alignment in Multimodal Language Prediction, Research Finds LLM Manuscript Scoring System Validated Against Peer-Review Outcomes at Major AI Conference Semantic Pyramid Indexing: Adaptive Query Depth for Streaming RAG in Vector Databases Deep Neural Networks Formulated via Non-Archimedean Analysis Offer New Universal Approximation Capabilities TuneJury: Open Metric Improves Music Generation Preference Alignment SACE Framework Introduces First Scale-Aware Concept Erasure for Visual Autoregressive Models to Prevent Catastrophic Semantic Collapse ControlMap: Controllable HD Map Generation Using Latent Diffusion for Traffic Simulation Akasha 2 Achieves 4x Faster Visual Synthesis with Hamiltonian-Inspired AI Architecture PURe Module Enhances Vision Networks by Adding Multiplicative Local Interactions New Unified Definition of AI Hallucination Pins It on Inaccurate World Modeling Attention, Not Model Scale, Drives Human-AI Alignment in Multimodal Language Prediction, Research Finds LLM Manuscript Scoring System Validated Against Peer-Review Outcomes at Major AI Conference Semantic Pyramid Indexing: Adaptive Query Depth for Streaming RAG in Vector Databases Deep Neural Networks Formulated via Non-Archimedean Analysis Offer New Universal Approximation Capabilities TuneJury: Open Metric Improves Music Generation Preference Alignment SACE Framework Introduces First Scale-Aware Concept Erasure for Visual Autoregressive Models to Prevent Catastrophic Semantic Collapse
Home ›› Topics ›› adversarial attacks

Topic

adversarial attacks

3 stories
New Research Defends LLMs from Extraction Attacks Using 'Knowledge Trap' Honeypot Technology
Artificial Intelligence #large language models#llm

New Research Defends LLMs from Extraction Attacks Using 'Knowledge Trap' Honeypot

A research paper by Dai and Dong introduces Knowledge Trap, a defense against large language model extraction attacks. It uses a Honeypot Knowledge Graph to redirect attackers' queries to low-value knowledge, reducing surrogate agreement by 6.2% on average while preserving legitimate user performance.

Jun 16, 2026 1 source
AutoDojo: Adaptive Attacks Expose Superficial Defenses and Structural Limits in LLM Agents Technology
Artificial Intelligence #llm#security

AutoDojo: Adaptive Attacks Expose Superficial Defenses and Structural Limits in LLM Agents

The AutoDojo framework adaptively optimizes indirect prompt injections against LLM agent defenses, revealing that many current defenses are superficial. Against a filter that reduces static attack success rate to 0%, AutoDojo recovers 28% overall and 64% on action-open tasks due to a structural limitation where injections can pose as ordinary data.

Jun 16, 2026 1 source
New Defense Keeps Attack Success Rate Below 4% for Adaptive Prompt Injection on LLM Agents Technology
Artificial Intelligence #prompt injection#ai security

New Defense Keeps Attack Success Rate Below 4% for Adaptive Prompt Injection on LLM Agents

Researchers propose RETA, a training-based defense that grounds LLM agent security on user tasks rather than attack patterns. Using chain-of-thought reasoning and red-teaming with diversity reward, RETA keeps average attack success rate below 4% across six adaptive attacks while preserving utility.

Jun 16, 2026 1 source