相关论文: FLIRT: Feedback Loop In-context Red Teaming

This work presents an open-source unified benchmarking and evaluation framework for text-to-image generation models, with a particular focus on the impact of metadata augmented prompts. Leveraging the DeepFashion-MultiModal dataset, we…

With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilities and improving…

Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method…

We introduce a novel approach for concept blending in pretrained text-to-image diffusion models, aiming to generate images at the intersection of multiple text prompts. At each time step during diffusion denoising, our algorithm forecasts…

The advancements in the domain of LLMs in recent years have surprised many, showcasing their remarkable capabilities and diverse applications. Their potential applications in various real-world scenarios have led to significant research on…

Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models. While adversarial example detection offers a lightweight…

Diffusion models have demonstrated remarkable capability in generating high-quality visual content from textual descriptions. However, since these models are trained on large-scale internet data, they inevitably learn undesirable concepts,…

The recent advances in diffusion models (DMs) have revolutionized the generation of realistic and complex images. However, these models also introduce potential safety hazards, such as producing harmful content and infringing data…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and…

In response to adversarial text attacks, attack detection models have been proposed and shown to successfully identify text modified by adversaries. Attack detection models can be leveraged to provide an additional check for NLP models and…

We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the semantics and syntax of…

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a…

As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in extended interaction settings that traditional single-turn safety evaluations fail to…

Questions and Answering forums such as Stack Overflow play an important role in supporting software developers in finding answers to queries related to issues such as software errors and bugs. However, searching through a large set of…

Conversational models that are generative and open-domain are particularly susceptible to generating unsafe content since they are trained on web-based social data. Prior approaches to mitigating this issue have drawbacks, such as…

Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit…