A survey on data augmentation for text classification
Data augmentation, the artificial creation of training data for machine learning by
transformations, is a widely studied research field across machine learning disciplines …
transformations, is a widely studied research field across machine learning disciplines …
Explainable ai: A review of machine learning interpretability methods
Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption,
with machine learning systems demonstrating superhuman performance in a significant …
with machine learning systems demonstrating superhuman performance in a significant …
Universal and transferable adversarial attacks on aligned language models
Because" out-of-the-box" large language models are capable of generating a great deal of
objectionable content, recent work has focused on aligning these models in an attempt to …
objectionable content, recent work has focused on aligning these models in an attempt to …
Are aligned neural networks adversarially aligned?
Large language models are now tuned to align with the goals of their creators, namely to be"
helpful and harmless." These models should respond helpfully to user questions, but refuse …
helpful and harmless." These models should respond helpfully to user questions, but refuse …
Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery
The strength of modern generative models lies in their ability to be controlled through
prompts. Hard prompts comprise interpretable words and tokens, and are typically hand …
prompts. Hard prompts comprise interpretable words and tokens, and are typically hand …
Red teaming language models with language models
Language Models (LMs) often cannot be deployed because of their potential to harm users
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …
Foundational challenges in assuring alignment and safety of large language models
This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …
language models (LLMs). These challenges are organized into three different categories …
Visual adversarial examples jailbreak aligned large language models
Warning: this paper contains data, prompts, and model outputs that are offensive in nature.
Recently, there has been a surge of interest in integrating vision into Large Language …
Recently, there has been a surge of interest in integrating vision into Large Language …
On the adversarial robustness of multi-modal foundation models
C Schlarmann, M Hein - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Multi-modal foundation models combining vision and language models such as Flamingo or
GPT-4 have recently gained enormous interest. Alignment of foundation models is used to …
GPT-4 have recently gained enormous interest. Alignment of foundation models is used to …
Automatically auditing large language models via discrete optimization
Auditing large language models for unexpected behaviors is critical to preempt catastrophic
deployments, yet remains challenging. In this work, we cast auditing as an optimization …
deployments, yet remains challenging. In this work, we cast auditing as an optimization …