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
449 results for “keyword:"tta"” in ICLR 2027. 126 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]AutoSkillDrain: Resource Amplification Attacks on LLM Agents via Malicious Skill Optimization▲3.0k2.33
[PDF]TARGETED FORGETTING: A FRAMEWORK FOR CLIENT- CLASS CENTRIC KNOWLEDGE REMOVAL IN FEDERATED LEARNING▼4.3k2.00
[PDF]Morpheus: Modality-Agnostic Adversarial Attack from Leaked Models in Federated Learning▲5.4k3.00
[PDF]Never Sampled, Always Accepted: Commitment Injection Through Top- Verification in Speculative Decoding▲3952.67
[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]Beyond Image-Wide Color Shifts: Scene-Compatible Semantic-Region Triggers for Backdoor Attacks▼1361.33
[PDF]Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies▼4.3k2.00
[PDF]Active Unlearning Probing: Label Inference Attack from the Client's Vantage in Federated Unlearning▲9.2k2.67
[PDF]Structure Becomes Signal: Document Hierarchy as a Learned Behavioral Channel in LLM Evaluators▼1.2k3.00
[PDF]From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models▼1.2k1.67
[PDF]Multi-Round SPEAR++: Exact Data Reconstruction from Model Updates across communication rounds in Federated Learning▼4.3k2.00
[PDF]ECLIPSE: Orthogonal Subspace Projection for Triggerless Bias Injection in Diffusion Models▼1.2k1.67
[PDF]CARAT: Class-Aware Robust Aggregation for Model-Poisoning-Resilient Federated Learning▼1.2k1.67
[PDF]Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH▼5.8k2.33
[PDF]Revealing Hidden Intent for Defending Text-to-Image Models against Adversarial Attacks▲3.0k2.33
[PDF]Clean Data, Dirty Secrets: Backdoor Transfer in LLM Distillation via Defect Amplification▼4.3k2.00
[PDF]Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning▲3.0k2.50
[PDF]Know Your Target before Striking: A Profile-Aware Adaptive Jailbreaking Framework for LLMs▼4.3k2.00
[PDF]DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection▲1.7k3.33
[PDF]Improved Certified Robustness and Adversarial Attacks for Rate-Encoded Spiking Neural Networks▲5.4k3.00
[PDF]Autonomous Red Teaming for Utility-Preserving Indirect Prompt Injection via Fine-Grained Diagnosis▼1.2k1.67
Withdrawn or desk rejected (126)
[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
[PDF]TypoShift: Open-Set Retrieval Hijacking and Attention Pathway Surgery for Text-to-Image Person Re-IdentificationWithdrawn2.00
[PDF]HAFT: Adversarial Robustness Benchmarking for Hindi Fact-Checking with Adaptive Attack SelectionDesk rejected
[PDF]It Takes Two to Tango: Backdoor Attack for Multimodal Diffusion Models via Cross-modal Collaborative TriggersWithdrawn1.67