Search Results for author:
Found 9 papers, 6 papers with code
Universal Prompt Optimizer for Safe Text-to-Image Generation
Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts.
Generative Pretraining in Multimodality
We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context.
Ranked #1 on
Visual Question Answering
on VQA v2
Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks
Text-to-image (T2I) diffusion models (DMs) have shown promise in generating high-quality images from textual descriptions.
Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations
Then we introduce BOSS, a Benchmark suite for Out-of-distribution robustneSS evaluation covering 5 tasks and 20 datasets.
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework
In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework.
Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
The detection of machine-generated text, especially from large language models (LLMs), is crucial in preventing serious social problems resulting from their misuse.
Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP
We discuss the deficiencies in previous work and propose our suggestions that the research on the Security-oriented adversarial NLP (SoadNLP) should: (1) evaluate their methods on security tasks to demonstrate the real-world concerns; (2) consider real-world attackers' goals, instead of developing impractical methods.
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting.
Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks
In this paper, we find two simple tricks that can make existing textual backdoor attacks much more harmful.
