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
2,656 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 576 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Exploiting the Law of Prägnanz in Diffusion Models to Prevent Unauthorized 3D Structure Reconstruction▲2623.67
[PDF]I CAN Debias: Uncovering and Enhancing Self-debiasing Mechanisms of Social Bias in LLMs▼1.2k1.67
[PDF]LIBERO-Risk: Safety-Critical Scenario Generation and Process-Level Evaluation for Vision-Language-Action Models▲3.0k2.33
[PDF]When Agents Learn the Wrong Lesson: Credit-Assignment Poisoning in Reflective LLM Agents▲5103.00
[PDF]Hijacking the Instruction Hierarchy in LLM Agents: From Semantic Injection to Persistent Compromise▼1.2k3.00
[PDF]Counterfactual Stress Testing of Behavioral Invariants in LLM Agents: A Study of Dynamic Authorization▼5.8k2.33
[PDF]To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse▲3.0k2.33
[PDF]Saturated Screening, Concentrated Cost: What a Full-Stack Ablation Table Reads in a Redundant Refusal Stack▼1.2k1.67
[PDF]Continuous Search Allocation: Jointly Shaping Probes and Updates for Query-Efficient Black-Box Video Attacks▼4.3k2.00
[PDF]Decodability Is Not Transferability: Uncovering Limitations in Graph Attribute Auditing via Orthogonal Alignment and Invertible Rotation Controls▲422.75
[PDF]FlyMark: Training-Free Invisible Watermarking of 3D Gaussian Splatting via a Fruit Fly Connectome▼4.5k2.67
[PDF]Stealth Still Leaves Traces: Exposing and Reducing Trigger Footprints in Graph Backdoor Attacks▼4.3k2.00
[PDF]Evolutionary Adversarial Attacks Meet LLMs: Semantic-aware Adaptive Optimization Against Vision-Language Pre-trained Models▼4.3k2.00
[PDF]LiveHumanRightsBench: Stress-Testing Reliability of LLM Judgments on Live Human-Rights Cases▼1.2k3.00
[PDF]BoundaryPlay: Improving Online Safety Self-Play via Counterfactual Request Construction▼4.3k2.00
[PDF]Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths▼5.8k2.33
[PDF]APTI-FL: Adversarial Perturbation Guided Trigger Inversion for Backdoor Detection in Federated Learning▼1611.50
[PDF]Traces of a Prompt: Uncovering and Mitigating Privacy Risks of Exposed States in TEE-Partitioned LLM Inference▼1.2k1.67
[PDF]GLED-Net: A Global-Local Evidence Decomposition Network for Multimodal Fake News Detection▼1361.33
Withdrawn or desk rejected (576)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected