NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
429 results for “keyword:"adversarial"” in ICLR 2027. 135 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving▼4.3k2.00
[PDF]When Measures Become Targets: Construct Validity Failures in Uncertainty-Based Hallucination Detection▼1361.33
[PDF]GraphSieve: Graph Purification via Attack-Agnostic Calibration across Perturbation Severities▼4.3k2.00
[PDF]TIDE: Defending Against Backdoor Data Poisoning via Dense Influence Subgraph Detection▼4.3k2.00
[PDF]Adaptive Admission Attacks on Semantic-ID Generative Recommenders: Detectability, Payload Size, and Downstream Promotion▼1.2k1.67
[PDF]Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations▲3952.67
[PDF]Toward Optimal Adversarial Attacks in Reinforcement Learning via Rate–Distortion Theory▼1.2k1.67
[PDF]ACE-Guard: Automated Co-Evolutionary Guardrails for LLM Security via Inference-Time Natural Language Gradients▼1361.33
[PDF]Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse▲3952.67
[PDF]AMEND: Attention Misalignment for Natural Adversarial Attacks against Object Detectors▼1.2k1.67
[PDF]Exposing Local Vulnerabilities in Neural Routing Solvers with an Efficient Black-Box Attack▲3952.67
[PDF]CLEAN FEATURE ANCHORING: MITIGATING THE ACCURACY–ROBUSTNESS TRADE-OFF BY SELF-DISTILLING A NATURALLY TRAINED MODEL▼3.7k2.25
[PDF]Fractal Signature Is a Property of the Generator, Not the Document: Split-Half Reliability Bounds for Scaling-Exponent AI-Text Detectors▼1.2k1.67
[PDF]FRA-Attack: Frequency-Domain Regularized Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs▼5.8k2.33
[PDF]MAGE: Margin-Aligned Gradient Energy for Target-Supervised Robust Adaptation of Vision-Language Models▼4.3k2.00
[PDF]CARS: Convergence-Aware Representation Steering for Multimodal Large Language Model Safety▲3952.67
[PDF]HAD²RL: Heterogeneous-Agent Dense Reinforcement Learning for Adversarial Failure Search of Detect-and-Avoid Systems▲1.7k3.33
[PDF]Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards▼4.5k2.67
[PDF]AdvSim2Real: Training Web Agents Against Adaptive Prompt Injection in a Web World Model▲6.1k2.00
[PDF]DART: Defense-Aware Red Teaming with a Critical Cue Bank for Open-World Adversarial Evaluation▼5.8k2.33
Withdrawn or desk rejected (135)
[PDF]DQ-PAD: Discriminative Quantized Prototype Alignment for Adversarial Patch DefenseWithdrawn1.67
[PDF]AcoustiGym: Physics-Based Acoustic Environment Generation for Robotic Policy EvaluationDesk rejected
[PDF]Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion ModelsWithdrawn1.67
[PDF]HAFT: Adversarial Robustness Benchmarking for Hindi Fact-Checking with Adaptive Attack SelectionDesk rejected