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122 results for “keyword:"defense"” in ICLR 2027. 42 withdrawn or desk rejected listed apart.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]ResSub: Dual-Level Backdoor Defense via Residual Alignment and Subspace Perturbation in Vertical Federated Learning▲13k2.33
[PDF]TransDiff: Plug-and-Play Adversarial Defense for No-Reference Image Quality Assessment via Calibrated Score Consensus▲5.4k3.00
[PDF]KV Compression Cannot Double as a Jailbreak Defense: The Harmfulness-then-Refusal Trajectory Guides Token Deletion▼5.8k2.33
[PDF]A Harmful Request Is Still a Request: Benign Fine-Tuning Rewrites How Aligned Models Begin to Answer▲3952.67
[PDF]What Did the Agent See? Implanting False Memories in Multimodal AI Agents through Black-Box Visual Attacks▲3952.67
[PDF]Defending Faces without Touching Pixels: Audio-Only Protection against Personalized Talking Face Generation▼5.8k2.33
[PDF]AgentHoneypot: Benchmarking Machine-Readable Content Injection and Provenance-Aware Authorization in Web Agents▼4.3k2.00
[PDF]BAPS: Boundary-Anchored Probabilistic Search for Reliable Decision-Based Attacks against Input-Noise Defenses▼1.2k1.67
[PDF]Learning Cyber Defense with Limited Interaction: An Empirical Study of Reflective Prompt Optimization▼1.2k1.67
[PDF]Beyond Jailbreak Rates: Harm Centric Evaluation of Multi Turn Jailbreak Attacks and Defenses▼4.3k2.00
[PDF]Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience▲3952.67
[PDF]Erase to Forge, Verify to Defend: Diffusion-based Forgery Attack and Self-verifiable Defense Mechanism▲6.6k3.33
[PDF]What makes a good anchor? Offline Anchor Selection for Test-Time Adversarial Robustness of CLIP▼5.8k2.33
[PDF]GenShield: Generalizable Visual Prompts for VLM Jailbreak Defense via Dual-View Adversarial Training▲3.0k2.33
[PDF]MEMSHIELD: NEUTRALIZING COALITIONAL MEMORY POISONING IN LLM AGENTS VIA CAUSAL REPRESENTATION REPAIR▼4.3k2.00
[PDF]FSPO: Fast Adversarial Training against Jailbreak Attacks via Soft Prompt Optimization▼4.5k2.67
[PDF]CCCV: Cross-Client Consistency Verification for High-Precision Backdoor Defense in Vertical Federated Learning▲3.0k2.33
[PDF]TIMBRE: Backdoor Defense in Federated Learning via Layer-wise Spectral Energy Distributions▲3952.67
[PDF]Valid Actions, Wrong Targets: Visual Attacks and Evidence-Based Defense for Web Agents▲9.2k2.67
[PDF]ImmuneCLIP: Adaptation-Stable Defense Against Backdoor Rebound in Purified CLIP Models▼4.3k2.00
[PDF]Defending Multi-turn Attacks On Large Language Models Through Active Intention Verification▲9.2k2.67
[PDF]ReQOR: Operator-Discrepancy Subspace Repair for Quantization-Conditioned Backdoors in Large Language Models▲3952.67
Withdrawn or desk rejected (42)
[PDF]From Rigid Carriers to Flexible Wrappers: Towards Output-Concealment Shadow-Activated Backdoor Attacks on MLLMsWithdrawn2.00
[PDF]FedHRA: Client-Side Purification and Hierarchical Robust Aggregation for Federated Backdoor Defense in Time-Series ClassificationWithdrawn1.67
[PDF]VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt AttacksWithdrawn1.67
[PDF]Before Acting, Change the State: Prospective State Intervention for Web Agents under Deceptive InterfacesDesk rejected