Thompson's"Reflections on Trusting Trust"showed that a compiler can be poisoned to reinsert its own backdoor, so that even recompiling clean source reproduces the Trojan. Today, substantial coding work is done by AI coding agents -- and increasingly, those agents generate new versions of themselves. We reconsider Thomp...
How does a multi-agent system evolve from a local deviation into collective loss of control? We propose an epidemic explanation organized around accidental mutation, contagion, and recovery. A spontaneous deviation creates a seed; communication enables other agents to adopt and retransmit its unsafe strategy; collectiv...
Xiang-Fan Wu, Zong-Hao Ying, Hui-Yu Wu et al.· 0 citations
The model is given a formal basis by transplanting the beta-factor model of common-cause failure from reliability engineering, a seven-step protocol whose outputs a third party can verify, a structural detectability analysis of a procurement-controls agent audited at three grades, and a Monte Carlo study of the model.
City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the incoming stream as ground truth. We study what happens when it is not. We formalise stealthy false data injection for city-scale pedestrian sensing, where the map from la...
Oscar Mogollon Gutierrez, Fatemeh Ghasemi, Mohammadhossein Homaei et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
AI-assisted claims can appear authoritative when evidence, analysis, human authorization, presentation, and correction history refer to different states. Provenance, attestation, and transparency expose history but alone do not specify the publication transition examined here. We develop Publication Authority as an exa...
Torsten Tiltack, Yi-Fei Dong, Kun Yu et al.· 0 citations
This work presents the first systematic robustness benchmark for local watermark robustness across 55 image transformations, and finds that signal distortions are often tolerated by the strongest methods, while geometric misalignment and generative local edits can completely impair payload recovery.
Kai Yao, Bence Szilágyi, Sebestyén Kamp et al.· 0 citations
The MAL Simulator, a cyber operation simulator based on the Meta Attack Language (MAL), found that the trained attacker policy could reach the designated targets more efficiently than the compared search methods, and that the trained defender agent induced lower costs than a naive heuristic agent under noisy alert cond...
Jakob Nyberg, Sandor Berglund, Andrei Buhaiu et al.· 0 citations
We test the performance of agents for automated network intrusion response in a cyber range intended for human operator training. The range implements an emulated networking environment with a variable network topology, red-team emulation and simulated user agents. The goal of the defensive agents is to prevent hosts i...
Jakob Nyberg, Teodor Sommestad, Andrei Buhaiu et al.· 0 citations
Deep neural networks (DNNs) have achieved great success in various applications due to their strong expressive power. However, recent studies have shown that DNNs are vulnerable to adversarial examples which are manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently, most such adversar...
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· 0 citations
In the United States, management of cybercrime-related consumer complaints increasingly falls on state and city governments given de-staffing of federal agencies. AI, and in particular, large language models (LLMs), shows promise for detecting cybercrime in text complaints, but often via specialized models that local g...
Two universal tool-based defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to identify and remove suspicious tools, and Normal Tool Recalling, a white-box method that restores the agent's original toolset prior to planning.
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for improving the quality of generated contents of Large Language Models (LLMs) by grounding responses in external knowledge, thus reducing hallucinations and factual errors. However, recent studies have highlighted a critical vulnerability: advers...
Xingyu Lyu, Jia-Yi Wang, Jian-Feng He et al.· 0 citations
