Security and privacy on generative data in aigc: A survey
The advent of artificial intelligence-generated content (AIGC) represents a pivotal moment in
the evolution of information technology. With AIGC, it can be effortless to generate high …
the evolution of information technology. With AIGC, it can be effortless to generate high …
Identifying and mitigating the security risks of generative ai
Every major technical invention resurfaces the dual-use dilemma—the new technology has
the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such …
the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such …
Editguard: Versatile image watermarking for tamper localization and copyright protection
In the era of AI-generated content (AIGC) malicious tampering poses imminent threats to
copyright integrity and information security. Current deep image watermarking while widely …
copyright integrity and information security. Current deep image watermarking while widely …
Towards understanding the interplay of generative artificial intelligence and the internet
The rapid adoption of generative Artificial Intelligence (AI) tools that can generate realistic
images or text, such as DALL-E, MidJourney, or ChatGPT, have put the societal impacts of …
images or text, such as DALL-E, MidJourney, or ChatGPT, have put the societal impacts of …
Protecting society from AI misuse: when are restrictions on capabilities warranted?
M Anderljung, J Hazell, M von Knebel - AI & SOCIETY, 2024 - Springer
Artificial intelligence (AI) systems will increasingly be used to cause harm as they grow more
capable. In fact, AI systems are already starting to help automate fraudulent activities, violate …
capable. In fact, AI systems are already starting to help automate fraudulent activities, violate …
A survey on detection of llms-generated content
The burgeoning capabilities of advanced large language models (LLMs) such as ChatGPT
have led to an increase in synthetic content generation with implications across a variety of …
have led to an increase in synthetic content generation with implications across a variety of …
Generative AI models should include detection mechanisms as a condition for public release
The new wave of 'foundation models'—general-purpose generative AI models, for
production of text (eg, ChatGPT) or images (eg, MidJourney)—represent a dramatic advance …
production of text (eg, ChatGPT) or images (eg, MidJourney)—represent a dramatic advance …
Leveraging optimization for adaptive attacks on image watermarks
Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and
engage in online spam or disinformation campaigns. Watermarking deters misuse by …
engage in online spam or disinformation campaigns. Watermarking deters misuse by …
Benchmarking the robustness of image watermarks
This paper investigates the weaknesses of image watermarking techniques. We present
WAVES (Watermark Analysis Via Enhanced Stress-testing), a novel benchmark for …
WAVES (Watermark Analysis Via Enhanced Stress-testing), a novel benchmark for …
Safe-sd: Safe and traceable stable diffusion with text prompt trigger for invisible generative watermarking
Z Ma, G Jia, B Qi, B Zhou - Proceedings of the 32nd ACM International …, 2024 - dl.acm.org
Recently, stable diffusion (SD) models have typically flourished in the field of image
synthesis and personalized editing, with a range of photorealistic and unprecedented …
synthesis and personalized editing, with a range of photorealistic and unprecedented …