OTora: New Framework Demonstrates Reasoning-Level Denial-of-Service Attacks on LLM Agents
Researchers have developed OTora, a red-teaming framework that can attack AI language model agents by forcing them to use excessive reasoning steps while maintaining correct task outputs. The attack, called Reasoning-Level Denial-of-Service (R-DoS), degrades system availability and latency without compromising accuracy. This work highlights a previously overlooked vulnerability in deployed autonomous AI systems where latency is operationally critical.
A new research paper on arXiv presents OTora, a two-stage framework for conducting Reasoning-Level Denial-of-Service (R-DoS) attacks against LLM-based autonomous agents. The attack works by injecting adversarial triggers that cause agents to invoke excessive tools and reasoning steps, dramatically increasing latency while preserving task correctness. In Stage I, the framework optimizes adversarial triggers using insertion-aware scoring and dynamic target co-evolution in both black-box and white-box settings. Stage II generates reasoning payloads through an in-context learning-guided genetic search that amplifies overthinking. Testing across multiple agent types (WebShop, Email, OS agents) and backbone models (LLaMA-70B, GPT-OSS-120B) demonstrated up to 10-fold increases in reasoning tokens and order-of-magnitude latency slowdowns while maintaining near-baseline task accuracy. The researchers also discuss potential mitigation strategies for detecting and constraining abnormal reasoning and latency patterns.
What's missing
The paper does not discuss the real-world prevalence or likelihood of such attacks in production environments, nor does it provide detailed analysis of the computational costs to attackers of mounting such attacks. Additionally, the effectiveness of the proposed mitigation strategies is not empirically evaluated in the paper.
What different sources said
- arXiv cs.LGCenter
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.