Program

Lunch Break

12:30–13:50
Lunch break

Session 1: Keynote and Opening

13:50–14:40 | Keynote
Prof. Giovanni Apruzzese
Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks
Large Language Models (LLMs) have revolutionized many aspects of our society. Many tasks encompassing document summarization or autonomous content generation can now benefit from the capabilities of LLMs. Among these, a domain in which LLMs are receiving increasing attention is that of scientific peer reviewing. Yet, usage of LLMs in this context must be done with due care: LLMs have certain blind spots which, if exploited, can lead to detrimental effects to the human requesting the service of an LLM. In this talk, I will outline the reasons why the author of a scientific paper may want to mislead an LLM tasked to review a given paper. Based on these reasons, I will then explain ways in which one can reach their goal via “hidden prompt injections”. Finally, I will discuss the results of a large-scale systematic analysis wherein we studied the impact of prompt-injection attacks against commercial LLMs (e.g., ChatGPT, Gemini). In doing so, I will also outline potential countermeasures—as well as counter-countermeasures. The takeaway is that blind reliance on LLMs for peer-review duties is strongly discouraged, and human oversight is still necessary.

14:40–14:50 | Logistics

14:50–15:00 | Opening Remarks
HotDiSec Organizing Committee

15:00–15:20 | Paper Presentation
Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data
Pouya Rajabi and Mohsen Toorani

Coffee Break

15:20–15:40
Coffee break

Session 2: Paper Presentations

15:40–16:00 | Paper Presentation
Robust Reputation-Driven Crowdsourced Federated Learning
Mouhamed Amine Bouchiha and Gregory Blanc

16:00–16:20 | Paper Presentation
Evaluating Membership Inference Attacks in Hierarchical Federated Learning
José Gouveia, Eva Maia, Ivone Amorim, and Isabel Praça

16:20–16:40 | Paper Presentation
Trusted Self-Healing DDoS Response for Cloud Services via Enclave-Backed Threshold Quorum Validation
Rrezearta Thaqi, Gabriele Lenzini, Marcus Voelp, and Blerim Rexha

16:40–17:00 | Paper Presentation
Federated Learning based Multivariate Time-series Intelligence for Generalized C2 Beaconing Detection
Jeetesh Gupta, Anum Talpur, Nicolas Imke, and Mathias Fischer

Awards and Closing

17:00–17:15 | Best Paper Award and Closing Remarks
HotDiSec Organizing Committee