{"total":22,"rows":[{"id":"2507.11097","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","created":"2025-07-15","cited_by_count":34,"area":"inference"},{"id":"2410.17175","title":"Remote Timing Attacks on Efficient Language Model Inference","created":"2024-10-22","cited_by_count":13,"area":"inference"},{"id":"2404.15420","title":"XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference","created":"2024-04-23","cited_by_count":12,"area":"inference"},{"id":"2508.17739","title":"Speculative Safety-Aware Decoding","created":"2025-08-25","cited_by_count":7,"area":"inference"},{"id":"2504.21228","title":"CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing","created":"2025-04-29","cited_by_count":2,"area":"inference"},{"id":"2607.19957","title":"HijackKV: New Threat in Position-Independent KV Cache Reuse","created":"2026-07-22","cited_by_count":2,"area":"inference"},{"id":"2608.01631","title":"Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression","created":"2026-08-03","cited_by_count":2,"area":"inference"},{"id":"2408.11308","title":"Defending against Jailbreak through Early Exit Generation of Large Language Models","created":"2024-08-21","cited_by_count":1,"area":"inference"},{"id":"2603.13420","title":"Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache","created":"2026-03-12","cited_by_count":1,"area":"inference"},{"id":"2605.11202","title":"Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing","created":"2026-05-11","cited_by_count":1,"area":"inference"},{"id":"2606.17872","title":"AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2607.21804","title":"Adversarial Prompts for Acceptance Collapse in Speculative Decoding","created":"2026-07-23","cited_by_count":1,"area":"inference"},{"id":"2608.01718","title":"LaCache: Robust Semantic Caching for LLM Serving","created":"2026-08-03","cited_by_count":1,"area":"inference"},{"id":"2605.27763","title":"A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving","created":"2026-05-26","cited_by_count":0,"area":"inference"},{"id":"2606.19755","title":"SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling","created":"2026-06-18","cited_by_count":0,"area":"inference"},{"id":"2606.25097","title":"Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion","created":"2026-06-23","cited_by_count":0,"area":"inference"},{"id":"2609.08306","title":"HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2609.31678","title":"When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression","created":"2026-09-16","cited_by_count":0,"area":"inference"},{"id":"2609.35908","title":"Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2610.08678","title":"Secure Speculative Decoding for Large Language Models","created":"2026-10-06","cited_by_count":0,"area":"inference"},{"id":"2610.09027","title":"Visual Memory Attacks Can Persist Through The KV Cache","created":"2026-10-06","cited_by_count":0,"area":"inference"},{"id":"2610.10929","title":"Speedbumps: Rejection Attacks on Speculative Decoding","created":"2026-10-07","cited_by_count":0,"area":"inference"}],"next_cursor":null}