Google Expands Its Bug Bounty Program to Tackle Artificial Intelligence Threats

Google has introduced that it is growing its Vulnerability Benefits Application (VRP) to reward scientists for acquiring attack situations customized to generative synthetic intelligence (AI) methods in an effort to bolster AI protection and security.

“Generative AI raises new and different concerns than conventional electronic security, such as the probable for unfair bias, model manipulation or misinterpretations of info (hallucinations),” Google’s Laurie Richardson and Royal Hansen mentioned.

Some of the groups that are in scope include things like prompt injections, leakage of sensitive information from training datasets, design manipulation, adversarial perturbation assaults that bring about misclassification, and model theft.

It is really worth noting that Google previously this July instituted an AI Purple Workforce to support tackle threats to AI devices as portion of its Protected AI Framework (SAIF).

Also introduced as part of its motivation to protected AI are efforts to strengthen the AI provide chain by way of present open-source security initiatives this kind of as Provide Chain Stages for Software package Artifacts (SLSA) and Sigstore.

“Digital signatures, these as these from Sigstore, which allow for end users to verify that the software program wasn’t tampered with or replaced,” Google explained.

“Metadata this kind of as SLSA provenance that inform us what’s in software program and how it was crafted, enabling buyers to make certain license compatibility, establish known vulnerabilities, and detect additional state-of-the-art threats.”

The enhancement will come as OpenAI unveiled a new inner Preparedness staff to “observe, consider, forecast, and guard” towards catastrophic threats to generative AI spanning cybersecurity, chemical, organic, radiological, and nuclear (CBRN) threats.

The two companies, alongside Anthropic and Microsoft, have also declared the creation of a $10 million AI Protection Fund, concentrated on advertising analysis in the discipline of AI protection.

Located this short article intriguing? Observe us on Twitter  and LinkedIn to go through extra exceptional content material we article.

Some parts of this article are sourced from:
thehackernews.com