Adobe targets AI security with bug bounty expansion for Content Credentials and Firefly – SiliconANGLE News

Creative software developer Adobe Inc. today announced an expansion of its bug bounty program to reward security researchers for discovering bugs specific to Content Credentials and Adobe Firefly.

Content Credentials, built on the C2PA open standard, are integrated across Adobe applications to enhance transparency and prevent the misuse of digital assets through the provision of tamper-evident metadata attached to digital content to verify its creation and editing history. Adobe Firefly is a family of creative, generative AI models used in standalone web applications and Adobe’s flagship products to enhance digital content creation.

The decision to expand the Adobe Bug Bounty program to Content Credentials reinforces Adobe’s resilience in implementing the standard against traditional risks and unique considerations that come with the provenance tool, such as the potential for intentional abuse of Content Credentials by incorrectly attaching them to the wrong asset.

For Firefly, the bug bounty program involves encouraging researchers to look for potential issues such as prompt injection, sensitive information disclosure or training data poisoning.

By engaging with the security community, Adobe hopes to gain additional insights into its generative AI technologies to provide valuable feedback to its internal teams and security program. The feedback will help identify key areas of focus and opportunities to reinforce security.

“The skills and expertise of security researchers play a critical role in enhancing security and now can help combat the spread of misinformation,” Dana Rao, executive vice president, general counsel and chief trust officer at Adobe, said in a blog post. “We are committed to working with the broader industry to help strengthen our Content Credentials implementation in Adobe Firefly and other flagship products to bring important issues to the forefront and encourage the development of responsible AI solutions.”

Adobe said the implementation of the expanded bug bounty program is in early stages toward ensuring the safe and secure development of generative AI.

“The future of technology is exciting, but there can be implications if these innovations are not built responsibly,” Daniel Ventura, product security manager for Adobe PSIRT & Bug Bounty, wrote in the post. “Our hope is that by incentivizing more security research in these areas, we’ll spark even more collaboration with the security community and others, to ultimately make AI safer for everyone.”

Photo: Chad Davis

This post was originally published on 3rd party site mentioned in the title of this site