ProofPoint Evasion - AI Case Study

Deploying AI models to edge devices can increase the attack surface of the system. Consider serving models in the cloud to reduce the level of access the adversary has to the model. Also consider computing features in the cloud to prevent gray-box attacks, where an adversary has access to the model preprocessing methods.

Implement logging of inputs and outputs of deployed AI models. When deploying AI agents, implement logging of the intermediate steps of agentic actions and decisions, data access and tool use, installation commands, and identity of the agent. Monitoring logs can help to detect security threats and mitigate impacts. Additionally, having logging enabled can discourage adversaries who want to remain undetected from utilizing AI resources.

Detect and block adversarial inputs or atypical queries that deviate from known benign behavior, exhibit behavior patterns observed in previous attacks or that come from potentially malicious IPs. Incorporate adversarial detection algorithms into the AI system prior to the AI model.

Require users to verify their identities before accessing a production model. Require authentication for API endpoints and monitor production model queries to ensure compliance with usage policies and to prevent model misuse.

Apply deepfake detection algorithms against any untrusted or user-provided data, especially in impactful applications such as biometric verification, to block generated content. Detectors may use a combination of approaches, including: - AI models trained to differentiate between real and deepfake content. - Identifying common inconsistencies in deepfake content, such as unnatural facial movements, audio mismatches, or pixel-level artifacts. - Biometrics analysis, such blinking, eye movements, and microexpressions.

Encrypt sensitive data such as AI models to protect against adversaries attempting to access sensitive data.

Preprocess all inference data to nullify or reverse potential adversarial perturbations.

Use techniques to make AI models robust to adversarial inputs such as adversarial training or network distillation.

Decreasing the fidelity of model outputs provided to the end user can reduce an adversary's ability to extract information about the model and optimize attacks for the model.

Limit the total number and rate of queries a user can perform.

Use an ensemble of models for inference to increase robustness to adversarial inputs. Some attacks may effectively evade one model or model family but be ineffective against others.

Incorporate multiple sensors to integrate varying perspectives and modalities to avoid a single point of failure susceptible to physical attacks.