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
122 results for “keyword:"defense"” in ICLR 2027. 42 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]GraphSieve: Graph Purification via Attack-Agnostic Calibration across Perturbation Severities▼4.3k2.00
[PDF]GradTrace: Gradient-Neighborhood Filtering for Backdoor Defense in Multimodal Instruction Tuning▼4.3k2.00
[PDF]MAGE: Margin-Aligned Gradient Energy for Target-Supervised Robust Adaptation of Vision-Language Models▼4.3k2.00
[PDF]HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models▼1.2k1.67
[PDF]K-Shield: Improving the Safety-Utility Trade-off in Refusal Steering with Local Null-Space Constraints▼4.5k2.67
[PDF]Backdoors Live in Shallow MLPs: State-Level Discriminative Attribution for Localized Pruning in LLM Backdoor Defense▼4.5k2.67
[PDF]Being Trapped then Mitigated: Defending Malicious Jailbreak Prompts via Embedded Honeypots in Text-to-Image Models▼5.8k2.33
[PDF]BlindClean: A Prior-Knowledge-Free Data Sanitization Method against Clean-Label Backdoor Attacks▼1361.33
[PDF]Trust-Aware Prototype-Guided Quantum Representation Learning for Backdoor-Resistant Medical Image Classification▼4.3k2.00
[PDF]STAD: Transferable Active Defense against Generative Image Steganography via Structural Feature Perturbations▼5.8k2.33
[PDF]ADAN: Adaptive Direction-Aware Noise for Defending Iterative Gradient Inversion Attacks▼1.2k1.67
[PDF]CICD-Guard: Contextual Intent Consensus for Robust Defense against LLM Jailbreak Attacks▼1361.33
[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]From Allow-or-Block to Risk-Adaptive Moderation: A Multi-Expert Safety Guardrail for Large Language Model Services▼5.8k2.33
[PDF]CamouPurifier: Zero-shot and Camouflage-Agnostic Defense Against Adversarial Camouflage Attacks on Monocular Depth Estimation▲5103.00
[PDF]EchoGhost: A Frequency-Structural Backdoor Attack and Spectral-Counterfactual Defense for Graph Neural Networks▼1361.33
[PDF]From Triggers to Antigens: An Immune-Inspired Framework for Continual Backdoor Defense▲3.0k2.33
[PDF]Is Decision Boundary a Reliable Signature for Graph Neural Network Ownership Verification?▼1.2k1.67
[PDF]Revealing Hidden Intent for Defending Text-to-Image Models against Adversarial Attacks▲3.0k2.33
[PDF]DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection▲1.7k3.33
[PDF]They Know When They're Unsure: Confidence-Gated Acceptance as a Two-Sided Defense against Sycophancy in Video Language Models▼1.2k1.67
Withdrawn or desk rejected (42)
[PDF]DQ-PAD: Discriminative Quantized Prototype Alignment for Adversarial Patch DefenseWithdrawn1.67
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00
[PDF]Tracing How Backdoors Are Learned: Poisoned Sample Detection via Information-Trajectory DistortionWithdrawn1.33