Skip to yearly menu bar Skip to main content


(7 events)   Time zone: Conference local time zone  
Show all
Toggle Poster Visibility
Oral
Thu Apr 23 10:30 AM -- 10:40 AM (-03) @ 201 C None
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
In Oral Session 1F Privacy and security
Bartłomiej Marek ⋅ Lorenzo Rossi ⋅ Vincent Hanke ⋅ Xun Wang ⋅ Michael Backes ⋅ Franziska Boenisch ⋅ Adam Dziedzic
[ OpenReview] 
Oral
Thu Apr 23 10:42 AM -- 10:52 AM (-03) @ 201 C None
Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
In Oral Session 1F Privacy and security
Guangnian Wan ⋅ Xinyin Ma ⋅ Gongfan Fang ⋅ Xinchao Wang
[ OpenReview] 
Oral
Thu Apr 23 10:54 AM -- 11:04 AM (-03) @ 201 C None
The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology
In Oral Session 1F Privacy and security
Aideen Fay ⋅ Inés García-Redondo ⋅ Qiquan Wang ⋅ Haim Dubossarsky ⋅ Anthea Monod
[ OpenReview] 
Oral
Thu Apr 23 11:06 AM -- 11:16 AM (-03) @ 201 C None
Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
In Oral Session 1F Privacy and security
Thibaud Gloaguen ⋅ Mark Vero ⋅ Robin Staab ⋅ Martin Vechev
[ OpenReview] 
Oral
Thu Apr 23 11:18 AM -- 11:28 AM (-03) @ 201 C None
LLM Fingerprinting via Semantically Conditioned Watermarks
In Oral Session 1F Privacy and security
Thibaud Gloaguen ⋅ Robin Staab ⋅ Nikola Jovanović ⋅ Martin Vechev
[ OpenReview] 
Oral
Thu Apr 23 11:30 AM -- 11:40 AM (-03) @ 201 C None
Steering the Herd: A Framework for LLM-based Control of Social Learning
In Oral Session 1F Privacy and security
Raghu Arghal ⋅ Kevin He ⋅ Shirin Saeedi Bidokhti ⋅ Saswati Sarkar
[ OpenReview] 
Oral
Thu Apr 23 11:42 AM -- 11:52 AM (-03) @ 201 C None
Every Language Model Has a Forgery-Resistant Signature
In Oral Session 1F Privacy and security
Matthew Finlayson ⋅ Xiang Ren ⋅ Swabha Swayamdipta
[ OpenReview]