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
124 results for “keyword:"poisoning"” in ICLR 2027. 20 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Trust Becomes a Liability: Bounding Persistent Influence under Temporally Adaptive Attacks in Federated Learning▲6.1k2.00
[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]A NOVEL BACKDOOR ATTACK AND DEFENSE TAR- GETING COST-EFFECTIVENESS OF LARGE LANGUAGE MODELS▼5.8k2.33
[PDF]The Privacy Fallacy of Crowdsourced Fine-tuning: Extracting Proprietary Data via Topic-Based Poisoning▲3.0k2.33
[PDF]GradTrace: Gradient-Neighborhood Filtering for Backdoor Defense in Multimodal Instruction Tuning▼4.3k2.00
[PDF]Granularity Blind Spots in Byzantine-Robust Federated Learning: Shapley-Guided Subspace Poisoning of Whole-Update Defenses▼4.3k2.00
[PDF]Activation Is Not Specificity: Structural Trajectory Backdoors in Tool-Calling LLM Agents▼4.3k2.00
[PDF]Trust-Aware Prototype-Guided Quantum Representation Learning for Backdoor-Resistant Medical Image Classification▼4.3k2.00
[PDF]Fragile by Distillation: Native-Objective Vicinal Alignment for Reliable Synthetic Sets▼5.8k2.33
[PDF]Chat Templates Are a Hidden Instruction Channel: Inference-Time Backdoors in LLM-Based Systems▲3952.67
[PDF]Restoring Backdoor Detection under Adaptive Attacks in Multimodal Large Language Models▼1.3k1.75
[PDF]Sweeping Promptable Spoofs under the DirtyRAG: A Practical, Query-Blind RAG Attack Done Right▼4.3k2.00
[PDF]Twenty-Five Samples to Blind a Guardrail: Stealthy Benign-Side Poisoning of Self-Adapting Safety Filters▲6.1k2.00
[PDF]EchoGhost: A Frequency-Structural Backdoor Attack and Spectral-Counterfactual Defense for Graph Neural Networks▼1361.33
[PDF]SAGE-RAG: Defending Retrieval-Augmented Generation with Trust Calibration and Graph Selection▼4.5k2.67
[PDF]MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair▼5.8k2.33
Withdrawn or desk rejected (20)
[PDF]When and How Often to Defend? On the Overlooked Role of Learning Rate Schedules in PoisoningWithdrawn1.33
[PDF]Parallax: A Two-Phase Defense for Memory-Augmented LLM Agents from a Causal PerspectiveWithdrawn1.67
[PDF]Right Answers, Poisoned Provenance: What Accuracy Misses in LLM-Based Multi-Agent ReasoningWithdrawn1.33
[PDF]ValidGS: Validation-Guided Defense Against View-Dependent Poisoning in 3D Gaussian SplattingWithdrawn2.00