Federico Torrielli

Federico Torrielli

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 September 2024 in International Journal of Human-Computer Studies
Verified
Journal Article
Open access
Amon RappAmon Rapp
Amon Rapp
CLChiara Di Lodovico
Chiara Di Lodovico
FTFederico Torrielli
Federico Torrielli
LCLuigi Di Caro
Luigi Di Caro

24 April 2025 in International Journal of Human–Computer Interaction
Verified
Journal Article
Closed access
CLChiara Di Lodovico
Chiara Di Lodovico
FTFederico Torrielli
Federico Torrielli
LCLuigi Di Caro
Luigi Di Caro
Amon RappAmon Rapp
Amon Rapp

11 July 2026 in Scientometrics
Verified
Journal Article
Open access
PDF file
FTFederico Torrielli
Federico Torrielli
SLStefano Locci
Stefano Locci
Amon RappAmon Rapp
Amon Rapp
LCLuigi Di Caro
Luigi Di Caro
Large language models are beginning to enter peer review as tools for summarizing manuscripts, drafting evaluations, and reducing reviewer workload. Yet this use creates a security problem specific to evaluative settings: the manuscript being judged can also contain hidden instructions that shape the model’s judgment. We investigate this risk through indirect prompt injection, where hidden text embedded in a manuscript is processed like a benign prompt by a public chatbot during review generation. We introduce an Author-Reviewer-Organizer framework that distinguishes author-side manipulation from organizer-side integrity checks, and use it to evaluate both offensive payloads, which steer reviews toward positive or negative judgments, and integrity-probing payloads, which trigger refusal, watermarking, or external-site redirection. The redirection payload is introduced here as a novel integrity-check mechanism. In experiments on 100 OpenReview papers, two public chatbot systems, five payload families, two custom prompt approaches, three injection positions, and five repeated runs per condition, we generate 42000 model outputs. Hidden instructions are highly effective: positive steering, refusal, and external-site redirection exceed 98% success on both systems; watermarking remains high but less reliable, reaching 94.27% on ChatGPT and 88.17% on Gemini; and negative steering is near-ceiling on ChatGPT but lower on Gemini. Vulnerability varies with payload design, model, and document position. These findings show that current models exhibit “contextual blindness”: they do not reliably separate manuscript content from embedded control text. This weakness threatens the validity of AI-assisted review, while also creating a dual-use channel that organizers may repurpose for detection. Peer-review systems that rely on public LLMs therefore require stronger safeguards between document content and instructions before they can be trusted in evaluative workflows.

20 September 2023
Verified
Conference Paper
Open access
LCLuigi Di Caro
Luigi Di Caro
Amon RappAmon Rapp
Amon Rapp
FTFederico Torrielli
Federico Torrielli
The GENERAL (GENerative, Explainable and Reasonable Artificial Learning) workshop, held at CHITALY 2023, delves into the advancements in General and Generative Artificial Intelligence (GGAI), with a focus on breakthroughs in natural language processing (NLP) and computer vision (CV). The workshop highlights the capabilities of Large Language Models (LLMs) and Latent Diffusion Models (LDMs) in generating human-like content across text and images. It emphasizes the importance of AI explainability, aiming to understand, explain, and control the complexities of these AI systems in terms of fairness, accountability, and transparency. The workshop encourages interdisciplinary collaboration across fields like HCI, psychology, social studies, and the arts to better understand AI’s societal and cultural impacts. Topics of interest include user perceptions of generative AIs, machine psychology, AI assistants, ethical issues in Generative AI, and safety and control mechanisms for large language models.


14 June 2023
Verified
Book Chapter
Closed access
PDF file
FTFederico Torrielli
Federico Torrielli
Amon RappAmon Rapp
Amon Rapp
LCLuigi Di Caro
Luigi Di Caro