Picture for Mintong Kang

Mintong Kang

AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents

Add code
Oct 22, 2024
Figure 1 for AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents
Figure 2 for AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents
Figure 3 for AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents
Figure 4 for AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents
Viaarxiv icon

EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage

Add code
Sep 17, 2024
Figure 1 for EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
Figure 2 for EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
Figure 3 for EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
Figure 4 for EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
Viaarxiv icon

$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning

Add code
Jul 08, 2024
Viaarxiv icon

Certifiably Byzantine-Robust Federated Conformal Prediction

Add code
Jun 04, 2024
Figure 1 for Certifiably Byzantine-Robust Federated Conformal Prediction
Figure 2 for Certifiably Byzantine-Robust Federated Conformal Prediction
Figure 3 for Certifiably Byzantine-Robust Federated Conformal Prediction
Figure 4 for Certifiably Byzantine-Robust Federated Conformal Prediction
Viaarxiv icon

COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits

Add code
Mar 17, 2024
Viaarxiv icon

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

Add code
Feb 12, 2024
Viaarxiv icon

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Add code
Jun 20, 2023
Viaarxiv icon

Fairness in Federated Learning via Core-Stability

Add code
Nov 03, 2022
Viaarxiv icon

Certifying Some Distributional Fairness with Subpopulation Decomposition

Add code
May 31, 2022
Figure 1 for Certifying Some Distributional Fairness with Subpopulation Decomposition
Figure 2 for Certifying Some Distributional Fairness with Subpopulation Decomposition
Figure 3 for Certifying Some Distributional Fairness with Subpopulation Decomposition
Figure 4 for Certifying Some Distributional Fairness with Subpopulation Decomposition
Viaarxiv icon

Data, Assemble: Leveraging Multiple Datasets with Heterogeneous and Partial Labels

Add code
Sep 25, 2021
Figure 1 for Data, Assemble: Leveraging Multiple Datasets with Heterogeneous and Partial Labels
Figure 2 for Data, Assemble: Leveraging Multiple Datasets with Heterogeneous and Partial Labels
Figure 3 for Data, Assemble: Leveraging Multiple Datasets with Heterogeneous and Partial Labels
Figure 4 for Data, Assemble: Leveraging Multiple Datasets with Heterogeneous and Partial Labels
Viaarxiv icon