Search Results for author:
Found 10 papers, 3 papers with code
SCANet: Correcting LEGO Assembly Errors with Self-Correct Assembly Network
To support research in this area, we present the LEGO Error Correction Assembly Dataset (LEGO-ECA), comprising manual images for assembly steps and instances of assembly failures.
DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization
The Style Generation module refreshes all styles at every training epoch, while the Style Removal module eliminates variations in the encoder's output features caused by input styles.
New Job, New Gender? Measuring the Social Bias in Image Generation Models
BiasPainter uses a diverse range of seed images of individuals and prompts the image generation models to edit these images using gender, race, and age-neutral queries.
A & B == B & A: Triggering Logical Reasoning Failures in Large Language Models
In addition, the test cases of LogicAsker can be further used to design demonstration examples for in-context learning, which effectively improves the logical reasoning ability of LLMs, e. g., 10\% for GPT-4.
BiasAsker: Measuring the Bias in Conversational AI System
Particularly, it is hard to generate inputs that can comprehensively trigger potential bias due to the lack of data containing both social groups as well as biased properties.
ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark
ChatGPT is a cutting-edge artificial intelligence language model developed by OpenAI, which has attracted a lot of attention due to its surprisingly strong ability in answering follow-up questions.
Transferable Unlearnable Examples
The unlearnable strategies have been introduced to prevent third parties from training on the data without permission.
Towards Fair Classification against Poisoning Attacks
We demonstrate that the fairly trained classifiers can be greatly vulnerable to such poisoning attacks, with much worse accuracy & fairness trade-off, even when we apply some of the most effective defenses (originally proposed to defend traditional classification tasks).
Probabilistic Categorical Adversarial Attack & Adversarial Training
To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discrete optimization problem to a continuous problem that can be solved efficiently by Projected Gradient Descent.
Defense Against Gradient Leakage Attacks via Learning to Obscure Data
However, federated learning is still under the risk of privacy leakage because of the existence of attackers who deliberately conduct gradient leakage attacks to reconstruct the client data.
