Adversarial Risk in the Generative AI Era Necessitates Dropping the Small Epsilon Ball
cs.LG, cs.CR
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
- A Large-Scale Exploit Instrumentation Study of AI/ML Supply Chain Attacks in Hugging Face Models
- Backdoor Attacks on Multiagent Collaborative Systems
- Motivating the Rules of the Game for Adversarial Example Research
- Explaining and Harnessing Adversarial Examples
- NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
- On Detecting Adversarial Perturbations
- FRAME : Comprehensive Risk Assessment Framework for Adversarial Machine Learning Threats
- Intriguing properties of neural networks
- The Risks of Machine Learning Systems
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- Demystifying LLM Supply Chain Vulnerabilities in the Wild: Distribution, Root Cause, and Real-World Impact
- Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
- Semantic Robustness Certification for Vision-Language Models
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis