Searcharxiv⌕ Search

arXiv subjects

Fady Copty

Publications and source records attributed to Fady Copty.

3 recordsLinked to original sources

Intent-Aware Protection for AI Agents

AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine whether an agent remains faithful to the purpose for which it was deployed. An action may contain no attack pattern and stay within granted permissions while still violating the agent's role, organizational constraints, or purpose. We introduce Intent- Aware Security, a framework that treats trusted agent intent as a first-class security object. We define Intent Preservation and Intent Drift, and operationalize them through an Intent Profile: an agent-specific representation extracted from organizational, role, and developer intent. We further introduce an Intent-Aware benchmark of 887 validated samples across 35 agents, built by a generation procedure that fixes ground-truth labels before LLM realization, and four Intent Profile-based protections: pre-execution detection, post-execution detection, input alignment, and system-prompt hardening. Across all evaluations, Intent Profile-based protection outperforms all profile-free baselines on the primary metric. On our benchmark, it raises four-class acro-F1 from 45% to 79% (Out-of-Scope F1 from 8% to 76%). On more than 10,000 executed AgentDojo trajectories, where ground truth comes from environment state, profile-based post-execution detection reaches 0.949 AUROC versus AlignmentCheck 0.909, 0.897 with raw agent configuration and 0.843 without context. Profile-based input alignment improves protection success by 7 points over DataFilter with a comparable benign utility. These results suggest that an agent's intended purpose can serve as a useful security reference for detecting and mitigating deviations from its deployed role and operational boundaries.

cs.CR↗

Deep ahead-of-threat virtual patching

Many applications have security vulnerabilities that can be exploited. It is practically impossible to find all of them due to the NP-complete nature of the testing problem. Security solutions provide defenses against these attacks through continuous application testing, fast-patching of vulnerabilities, automatic deployment of patches, and virtual patching detection techniques deployed in network and endpoint security tools. These techniques are limited by the need to find vulnerabilities before the black-hats. We propose an innovative technique to virtually patch vulnerabilities before they are found. We leverage testing techniques for supervised-learning data generation, and show how artificial intelligence techniques can use this data to create predictive deep neural-network models that read an application's input and predict in real time whether it is a potential malicious input. We set up an ahead-of-threat experiment in which we generated data on old versions of an application, and then evaluated the predictive model accuracy on vulnerabilities found years later. Our experiments show ahead-of-threat detection on LibXML2 and LibTIFF vulnerabilities with 91.3% and 93.7% accuracy, respectively. We expect to continue work on this field of research and provide ahead-of-threat virtual patching for more libraries. Success in this research can change the current state of endless racing after application vulnerabilities and put the defenders one step ahead of the attackers

cs.CR↗

Shakedown: compiler-based moving target protection for Return Oriented Programing attacks on an industrial IoT device

Cybercriminals use Return Oriented Programming techniques to attack systems and IoT devices. While defenses have been developed, not all of them are applicable to constrained devices. We present Shakedown, which is a compile-time randomizing build tool which creates several versions of the binary, each with a distinct memory layout. An attack developed against one device will not work on another device which has a different memory layout. We tested Shakedown on an industrial IoT device and shown that its normal functionality remained intact while an exploit was blocked.

cs.CR↗