{"ID":2824347,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.23779","arxiv_id":"2512.23779","title":"Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark","abstract":"Large Language Models (LLMs) can be driven into over-generation, emitting thousands of tokens before producing an end-of-sequence (EOS) token. This degrades answer quality, inflates latency and cost, and can be weaponized as a denial-of-service (DoS) attack. Recent work has begun to study DoS-style prompt attacks, but typically focuses on a single attack algorithm or assumes white-box access, without an attack-side benchmark that compares prompt-based attackers in a black-box, query-only regime with a known tokenizer. We introduce such a benchmark and study two prompt-only attackers. The first is an Evolutionary Over-Generation Prompt Search (EOGen) that searches the token space for prefixes that suppress EOS and induce long continuations. The second is a goal-conditioned reinforcement learning attacker (RL-GOAL) that trains a network to generate prefixes conditioned on a target length. To characterize behavior, we introduce Over-Generation Factor (OGF): the ratio of produced tokens to a model's context window, along with stall and latency summaries. EOGen discovers short-prefix attacks that raise Phi-3 to OGF = 1.39 +/- 1.14 (Success@\u003e=2: 25.2%); RL-GOAL nearly doubles severity to OGF = 2.70 +/- 1.43 (Success@\u003e=2: 64.3%) and drives budget-hit non-termination in 46% of trials.","short_abstract":"Large Language Models (LLMs) can be driven into over-generation, emitting thousands of tokens before producing an end-of-sequence (EOS) token. This degrades answer quality, inflates latency and cost, and can be weaponized as a denial-of-service (DoS) attack. Recent work has begun to study DoS-style prompt attacks, but...","url_abs":"https://arxiv.org/abs/2512.23779","url_pdf":"https://arxiv.org/pdf/2512.23779v2","authors":"[\"Manu\",\"Yi Guo\",\"Kanchana Thilakarathna\",\"Nirhoshan Sivaroopan\",\"Jo Plested\",\"Tim Lynar\",\"Jack Yang\",\"Wangli Yang\"]","published":"2025-12-29T13:42:08Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}