Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Manu, Guo, Yi, Thilakarathna, Kanchana, Sivaroopan, Nirhoshan, Plested, Jo, Lynar, Tim, Yang, Jack, Yang, Wangli
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908772022091776
author Manu
Guo, Yi
Thilakarathna, Kanchana
Sivaroopan, Nirhoshan
Plested, Jo
Lynar, Tim
Yang, Jack
Yang, Wangli
author_facet Manu
Guo, Yi
Thilakarathna, Kanchana
Sivaroopan, Nirhoshan
Plested, Jo
Lynar, Tim
Yang, Jack
Yang, Wangli
contents 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@>=2: 25.2%); RL-GOAL nearly doubles severity to OGF = 2.70 +/- 1.43 (Success@>=2: 64.3%) and drives budget-hit non-termination in 46% of trials.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23779
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark
Manu
Guo, Yi
Thilakarathna, Kanchana
Sivaroopan, Nirhoshan
Plested, Jo
Lynar, Tim
Yang, Jack
Yang, Wangli
Cryptography and Security
Artificial Intelligence
Machine Learning
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@>=2: 25.2%); RL-GOAL nearly doubles severity to OGF = 2.70 +/- 1.43 (Success@>=2: 64.3%) and drives budget-hit non-termination in 46% of trials.
title Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2512.23779