Against The Achilles' Heel: A Survey on Red Teaming for Generative Models
Generative models are rapidly gaining popularity and being integrated into everyday
applications, raising concerns over their safe use as various vulnerabilities are exposed. In …
applications, raising concerns over their safe use as various vulnerabilities are exposed. In …
A survey of backdoor attacks and defenses on large language models: Implications for security measures
Large Language Models (LLMs), which bridge the gap between human language
understanding and complex problem-solving, achieve state-of-the-art performance on …
understanding and complex problem-solving, achieve state-of-the-art performance on …
Enhancing federated semi-supervised learning with out-of-distribution filtering amidst class mismatches
Federated Learning (FL) has gained prominence as a method for training models on edge
computing devices, enabling the preservation of data privacy by eliminating the need to …
computing devices, enabling the preservation of data privacy by eliminating the need to …
Artwork protection against neural style transfer using locally adaptive adversarial color attack
Neural style transfer (NST) generates new images by combining the style of one image with
the content of another. However, unauthorized NST can exploit artwork, raising concerns …
the content of another. However, unauthorized NST can exploit artwork, raising concerns …
Clean-label backdoor attack and defense: An examination of language model vulnerability
Prompt-based learning, a paradigm that creates a bridge between pre-training and fine-
tuning stages, has proven to be highly effective concerning various NLP tasks, particularly in …
tuning stages, has proven to be highly effective concerning various NLP tasks, particularly in …
Mitigating backdoor threats to large language models: Advancement and challenges
The advancement of Large Language Models (LLMs) has significantly impacted various
domains, including Web search, healthcare, and software development. However, as these …
domains, including Web search, healthcare, and software development. However, as these …
[PDF][PDF] A comprehensive evaluation and comparison of enhanced learning methods
This paper provides a comprehensive evaluation and comparison of current reinforcement
learning methods. By analyzing the strengths and weaknesses of the main methods, such as …
learning methods. By analyzing the strengths and weaknesses of the main methods, such as …
Large Model Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends
Large Model (LM) agents, powered by large foundation models such as GPT-4 and DALL-E
2, represent a significant step towards achieving Artificial General Intelligence (AGI). LM …
2, represent a significant step towards achieving Artificial General Intelligence (AGI). LM …
Weak-to-Strong Backdoor Attack for Large Language Models
Despite being widely applied due to their exceptional capabilities, Large Language Models
(LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce …
(LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce …
Unlearning backdoor attacks for llms with weak-to-strong knowledge distillation
Parameter-efficient fine-tuning (PEFT) can bridge the gap between large language models
(LLMs) and downstream tasks. However, PEFT has been proven vulnerable to malicious …
(LLMs) and downstream tasks. However, PEFT has been proven vulnerable to malicious …