5 citations · 10 across the 6 of their papers we have counts for
6 papers
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
Yanting Wang, Wei Zou, Jinyuan Jia
Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support sample…
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
Yanting Wang, Hongye Fu, Wei Zou +1
Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D poi…
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
Bochuan Cao, Changjiang Li, Ting Wang +3
Diffusion-based image generation models, such as Stable Diffusion or DALL-E 2, are able to learn from given images and generate high-quality samples following the guidance from pro…
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?
Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu +5
Large Language Models (LLMs) have achieved unprecedented performance in Natural Language Generation (NLG) tasks. However, many existing studies have shown that they could be misuse…
PORE: Provably Robust Recommender Systems against Data Poisoning Attacks
Jinyuan Jia, Yupei Liu, Yuepeng Hu +1
Data poisoning attacks spoof a recommender system to make arbitrary, attacker-desired recommendations via injecting fake users with carefully crafted rating scores into the recomme…
REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service
Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong
Encoder as a service is an emerging cloud service. Specifically, a service provider first pre-trains an encoder (i.e., a general-purpose feature extractor) via either supervised le…