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
2,657 results for “area:"alignment, fairness, safety, privacy, and societal considerations"” in ICLR 2027. 575 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ProtoLoRA: Visual-Prototype-Guided LoRA Backdoor Attack against Vision–Language Models▼5.8k2.33
[PDF]A Harmful Request Is Still a Request: Benign Fine-Tuning Rewrites How Aligned Models Begin to Answer▲3952.67
[PDF]A Jailbreak Success Coordinate Outside the Refusal Subspace: Decodable Before Generation, Reachable from the Input▼5.8k2.33
[PDF]Rethinking Cross-Task Knowledge Sharing: Medical Federated Multi-Task Learning with the Input Space Knowledge Decoupling▼5.8k2.33
[PDF]Pretending to Think: Unmasking and Eliminating Post-Hoc Rationalization in LLM Safety Chain of Thought▼4.3k2.00
[PDF]Auditing Accuracy Change in Human–AI Decision-Making: Partial Identification and Behavioral Constraints▼1.2k1.67
[PDF]From Risk Recognition to Safer Generation: Compete–Split–Fuse for Selective Representation Coordination▼4.3k2.00
[PDF]Same Conversation, Different Actions: Phase-Conditioned Causal Steering for Multi-Turn LLM Safety▲1.7k3.33
[PDF]Namesakes on the List: Composition Amplification and Target-Decoy Calibration in Sanctions Name Screening▲6.1k2.00
[PDF]FIAPBA: Federated Instruction-Assisted Persistent Backdoor Attacks against Large Language Models▼4.3k2.00
[PDF]ActionPatch: Distilling Adversarial Instructions into Visual Patches for GUI Agent Hijacking▲432.75
[PDF]Can Useful Work Be the Attack? CUCKOO SKILLS: PARASITIC TOKEN-COST ATTACKS ON LLM AGENTS▲3.0k2.33
[PDF]Learning Before the First Success: Bidirectional Progress-Guided Training from Failed Cyber Interactions▼1361.33
[PDF]CoSA: Characterizing the Conflict of Skills Attack in Real-World LLM Agent Skill Ecosystems▼5.8k2.33
[PDF]What Did the Agent See? Implanting False Memories in Multimodal AI Agents through Black-Box Visual Attacks▲3952.67
[PDF]Does My LLM Obey Me? Falsification-Based Attribution Tests for Prompt-Based Behavioral Conditioning▼1361.33
[PDF]DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation▼1.2k1.67
[PDF]User Message Fine-tuning: Implanting Beliefs, Preferences, and Alignment in LLMs by Training on User Messages▲3952.67
Withdrawn or desk rejected (575)
[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