77 citations · 183 across the 39 of their papers we have counts for
40 papers
Integrity of peer-to-peer distributed LLM inference under malicious nodes
Mert Cihangiroglu, Antonino Nocera
Peer-to-peer distributed inference executes a Large Language Model (LLM) on pooled consumer hardware by spreading its layers across many nodes. Every request passes through nodes t…
CVE-TTP KG: Knowledge Graph Linking Software Vulnerabilities to Attack Behaviors
Swati Yadav, Dincy R. Arikkat, Basant Agarwal +3
In the evolving threat landscape, adversaries exploit software vulnerabilities to launch sophisticated attacks, challenging traditional defenses. Although databases like CVE and NV…
An AI-Based Solution for Secure Service Provisioning in IoT
Marco Arazzi, Mert Cihangiroglu, Serena Nicolazzo +2
As the Internet of Things (IoT) continues its rapid expansion, the attack surface grows accordingly, with emerging threats targeting smart objects and their interactions. In this e…
A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution
Jithin S., Roshin Sleeba C., Anvin Mariya P. B. +4
Malware classification remains a challenging problem due to its inherent heterogeneity, the presence of packed binaries, and the diverse distribution of malware families. Tradition…
GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking
Aman Anifer, Vignesh Kumar Kembu, Vishnu M +4
Large Language Models (LLMs) constitute pivotal components within the AI-dominated information technology ecosystem. To mitigate risks associated with harmful or policy-violating o…
LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections (Full Version)
Mert Cihangiroglu, Alessandro Pegoraro, Phillip Rieger +2
Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server. However, the cut-layer interface introduces a key challenge…
You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation
Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera +2
Public repositories now distribute thousands of specialized Low-Rank Adaptation (LoRA) modules, but a third-party adapter routinely arrives without the refusal behavior the same ad…
Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
Nandakrishna Giri, Asmitha K. A., Serena Nicolazzo +2
Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address this vulnerability, we propose…
Security in LLM-as-a-Judge: A Comprehensive SoK
Aiman Al Masoud, Antony Anju, Marco Arazzi +6
LLM-as-a-Judge (LaaJ) is a novel paradigm in which powerful language models are used to assess the quality, safety, or correctness of generated outputs. While this paradigm has sig…
Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards
Aiman Al Masoud, Marco Arazzi, Simone Germani +1
Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential dependencies, which making it chal…
SecureBreak -- A dataset towards safe and secure models
Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera
Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe…
SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation
Aiman Al Masoud, Marco Arazzi, Antonino Nocera
Retrieval-Augmented Generation (RAG) has attracted significant attention due to its ability to combine the generative capabilities of Large Language Models (LLMs) with knowledge ob…
LoRA as Oracle
Marco Arazzi, Antonino Nocera
Practitioners increasingly deploy neural networks they did not train, and must audit them after the fact for hidden backdoors, without the training pipeline, the poisoned data, or…
GShield: Mitigating Poisoning Attacks in Federated Learning
Sameera K. M., Serena Nicolazzo, Antonino Nocera +2
Federated Learning (FL) has recently emerged as a revolutionary approach to collaborative training Machine Learning models. In particular, it enables decentralized model training w…
Are LLMs Truly Multilingual? Exploring Zero-Shot Multilingual Capability of LLMs for Information Retrieval: An Italian Healthcare Use Case
Vignesh Kumar Kembu, Pierandrea Morandini, Marta Bianca Maria Ranzini +1
Large Language Models (LLMs) have become a key topic in AI and NLP, transforming sectors like healthcare, finance, education, and marketing by improving customer service, automatin…
SoK: The Last Line of Defense: On Backdoor Defense Evaluation
Gorka Abad, Marina Krček, Stefanos Koffas +7
Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been…
CTI Dataset Construction from Telegram
Dincy R. Arikkat, Sneha B. T., Serena Nicolazzo +4
Cyber Threat Intelligence (CTI) enables organizations to anticipate, detect, and mitigate evolving cyber threats. Its effectiveness depends on high-quality datasets, which support…
Enhancing Android Malware Detection with Retrieval-Augmented Generation
Saraga S., Anagha M. S., Dincy R. Arikkat +4
The widespread use of Android applications has made them a prime target for cyberattacks, significantly increasing the risk of malware that threatens user privacy, security, and de…
When Forgetting Triggers Backdoors: A Clean Unlearning Attack
Marco Arazzi, Antonino Nocera, Vinod P
Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the un…
Security through the Eyes of AI: How Visualization is Shaping Malware Detection
Matteo Brosolo, Asmitha K. A., Mauro Conti +5
Malware, a persistent cybersecurity threat, increasingly targets interconnected digital systems such as desktop, mobile, and IoT platforms through sophisticated attack vectors. By…
XBreaking: Understanding how LLMs security alignment can be broken
Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera +1
Large Language Models are fundamental actors in the modern IT landscape dominated by AI solutions. However, security threats associated with them might prevent their reliable adopt…
DroidTTP: Mapping Android Applications with TTP for Cyber Threat Intelligence
Dincy R Arikkat, Vinod P., Rafidha Rehiman K. A. +4
The widespread adoption of Android devices for sensitive operations like banking and communication has made them prime targets for cyber threats, particularly Advanced Persistent T…
Privacy Preserving and Robust Aggregation for Cross-Silo Federated Learning in Non-IID Settings
Marco Arazzi, Mert Cihangiroglu, Antonino Nocera
Federated Averaging remains the most widely used aggregation strategy in federated learning due to its simplicity and scalability. However, its performance degrades significantly i…
Secure Federated Data Distillation
Marco Arazzi, Mert Cihangiroglu, Serena Nicolazzo +1
Dataset Distillation (DD) is a powerful technique for reducing large datasets into compact, representative synthetic datasets, accelerating Machine Learning training. However, trad…