{"total":18,"rows":[{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2505.13763","title":"Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations","created":"2025-05-19","cited_by_count":41,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2507.12691","title":"Benchmarking Deception Probes via Black-to-White Performance Boosts","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2506.24068","title":"STACK: Adversarial Attacks on LLM Safeguard Pipelines","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2505.14300","title":"Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2510.21531","title":"Probe-based Fine-tuning for Reducing Toxicity","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2607.20379","title":"Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2608.21664","title":"Measuring Activation Control in Large Language Models","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.29458","title":"Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2606.09411","title":"Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.09563","title":"PRISM: Recovering Instruction Sets from Language Model Activations","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.26175","title":"EADC: Evaluation of Advanced and Deep-level Compliance in Large Language Models","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}