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
131 results for “keyword:"prompt injection"” in ICLR 2027. 22 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LLM Agent Refusal Can be Harmful: An Availability Attack through MITM Tampering on Remote MCP Services▼4.3k2.00
[PDF]Do Detailed Guard Denials Help Bypass Guardrails? Evaluating Runtime Feedback in DeepSeek Harness▼4.3k2.00
[PDF]Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance▲5103.00
[PDF]LLM-DE: Jailbreaking LLM-based Malware Detection via Prompt Injection and Safety Alignment Exploitation▼1361.33
[PDF]Endogenous Byzantine Faults: Measuring and Containing Fault Contagion in LLM Multi-Agent Systems▲3.0k2.50
[PDF]Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models▲6.1k2.00
[PDF]ArenaWeaver: Automatic Generation of Environments and Attacks for Prompt Injection Evaluation at Scale▼4.5k2.67
[PDF]AgentHoneypot: Benchmarking Machine-Readable Content Injection and Provenance-Aware Authorization in Web Agents▼4.3k2.00
[PDF]SpanGuard: Decoupling Instruction Localization from Authorization for Lightweight IPI Defense▼4.3k2.00
[PDF]BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views▼5.9k2.50
[PDF]Unified Hierarchical Red-Teaming: Strategy Search and Evidence-Guided Policy Evolution▼4.3k2.00
[PDF]Acting Through Others: Evaluating Agent Competence and Safety in Socially Distributed Environments▼1.2k3.00
[PDF]From Untrusted Content to Accepted Instructions: Security Risks of Context Compaction in LLM Agents▼3.7k2.25
[PDF]AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents▼4.3k2.00
[PDF]Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?▲3.0k2.33
[PDF]Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience▲3972.67
[PDF]ROWGATE: DETERMINISTIC ROW-LEVEL ACCESS CONTROL FOR LLM QUERY AGENTS OVER FEDERATED SOURCES▼1.2k1.67
[PDF]SAFI: A Controlled Method for Evaluating Payload Placement and Task Framing in File-Injection Attacks on LLM Agents▼1361.33
[PDF]Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection▲5103.00
Withdrawn or desk rejected (22)
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00
[PDF]Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy RewardsWithdrawn1.67
[PDF]ClickShield: A Firewall for Multimodal Computer-use Agents Against Dual Prompt InjectionWithdrawn1.67
[PDF]A Review of Indirect Prompt Injection and its Defenses Using Large-Scale Public Red-Teaming Competition DataWithdrawn2.00