Skip to yearly menu bar Skip to main content


(7 events)   Timezone:  
Show all
The 2026 schedule is still incomplete
Toggle Poster Visibility
Oral
Thu Apr 23 06:30 AM -- 06:40 AM (PDT) None
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
In Oral Session 1F
Bartłomiej Marek · Lorenzo Rossi · Vincent Hanke · Xun Wang · Michael Backes · Franziska Boenisch · Adam Dziedzic
[ OpenReview] 
Oral
Thu Apr 23 06:42 AM -- 06:52 AM (PDT) None
Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
In Oral Session 1F
Guangnian Wan · Xinyin Ma · Gongfan Fang · Xinchao Wang
[ OpenReview] 
Oral
Thu Apr 23 06:54 AM -- 07:04 AM (PDT) None
The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology
In Oral Session 1F
Aideen Fay · Inés García-Redondo · Qiquan Wang · Haim Dubossarsky · Anthea Monod
[ OpenReview] 
Oral
Thu Apr 23 07:06 AM -- 07:16 AM (PDT) None
Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
In Oral Session 1F
Thibaud Gloaguen · Mark Vero · Robin Staab · Martin Vechev
[ OpenReview] 
Oral
Thu Apr 23 07:18 AM -- 07:28 AM (PDT) None
LLM Fingerprinting via Semantically Conditioned Watermarks
In Oral Session 1F
Thibaud Gloaguen · Robin Staab · Nikola Jovanović · Martin Vechev
[ OpenReview] 
Oral
Thu Apr 23 07:30 AM -- 07:40 AM (PDT) None
Steering the Herd: A Framework for LLM-based Control of Social Learning
In Oral Session 1F
Raghu Arghal · Kevin He · Shirin Saeedi Bidokhti · Saswati Sarkar
[ OpenReview] 
Oral
Thu Apr 23 07:42 AM -- 07:52 AM (PDT) None
Every Language Model Has a Forgery-Resistant Signature
In Oral Session 1F
Matthew Finlayson · Xiang Ren · Swabha Swayamdipta
[ OpenReview]