167 citations · 244 across the 13 of their papers we have counts for
13 papers
Blue Teaming Function-Calling Agents
Greta Dolcetti, Giulio Zizzo, Sergio Maffeis
We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three different attacks, and we measure t…
Clutch Control: An Attention-based Combinatorial Bandit for Efficient Mutation in JavaScript Engine Fuzzing
Myles Foley, Sergio Maffeis, Muhammad Fakhrur Rozi +1
JavaScript engines are widely used in web browsers, PDF readers, and server-side applications. The rise in concern over their security has led to the development of several targete…
Detecting APT Malware Command and Control over HTTP(S) Using Contextual Summaries
Almuthanna Alageel, Sergio Maffeis, Imperial College London
Advanced Persistent Threats (APTs) are among the most sophisticated threats facing critical organizations worldwide. APTs employ specific tactics, techniques, and procedures (TTPs)…
Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
Greta Dolcetti, Vincenzo Arceri, Eleonora Iotti +3
Large Language Models (LLMs) are one of the most promising developments in the field of artificial intelligence, and the software engineering community has readily noticed their po…
APIRL: Deep Reinforcement Learning for REST API Fuzzing
Myles Foley, Sergio Maffeis
REST APIs have become key components of web services. However, they often contain logic flaws resulting in server side errors or security vulnerabilities. HTTP requests are used as…
HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment
Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis
With the introduction of the transformers architecture, LLMs have revolutionized the NLP field with ever more powerful models. Nevertheless, their development came up with several…
Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
Janvi Thakkar, Giulio Zizzo, Sergio Maffeis
Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work address…
Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience
Janvi Thakkar, Giulio Zizzo, Sergio Maffeis
Machine learning models are being used in an increasing number of critical applications; thus, securing their integrity and ownership is critical. Recent studies observed that adve…
VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection
Hazim Hanif, Sergio Maffeis
This paper presents VulBERTa, a deep learning approach to detect security vulnerabilities in source code. Our approach pre-trains a RoBERTa model with a custom tokenisation pipelin…
Certified Federated Adversarial Training
Giulio Zizzo, Ambrish Rawat, Mathieu Sinn +2
In federated learning (FL), robust aggregation schemes have been developed to protect against malicious clients. Many robust aggregation schemes rely on certain numbers of benign c…
A Hybrid Graph Neural Network Approach for Detecting PHP Vulnerabilities
Rishi Rabheru, Hazim Hanif, Sergio Maffeis
This paper presents DeepTective, a deep learning approach to detect vulnerabilities in PHP source code. Our approach implements a novel hybrid technique that combines Gated Recurre…
Adversarial Attacks on Time-Series Intrusion Detection for Industrial Control Systems
Giulio Zizzo, Chris Hankin, Sergio Maffeis +1
Neural networks are increasingly used for intrusion detection on industrial control systems (ICS). With neural networks being vulnerable to adversarial examples, attackers who wish…
Deep Latent Defence
Giulio Zizzo, Chris Hankin, Sergio Maffeis +1
Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems a…