Zero-Query Transferable Pretend Benign Attacks with Amortized Online Generation for Cooperative Perception
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/windlinsherlock/Pretend-Benign
Terminology
Sources
- All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference
- Linking Modality Isolation in Heterogeneous Collaborative Perception
- CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion
- CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions
- From Stealthy Data Fabrication to Unsafe Driving: Realistic Scenario Attacks on Collaborative Perception
- Adversarial Trust Poisoning in Vehicular Collaborative Perception
- Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception
- GLST: Defending Confidence-Driven V2X Collaborative Perception Against Stealthy Multi-Attacker Feature Injection
- Explaining and Harnessing Adversarial Examples
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Distilling the Knowledge in a Neural Network
- Towards Deep Learning Models Resistant to Adversarial Attacks
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents