WHISPER 2026

Artificial Intelligence (AI) systems are increasingly integrated into a wide range of domains, including sensitive and safety-critical tasks, reshaping the landscape of information security. From synthetic content generation to intelligent system deployment, AI technologies now influence every layer of communication, data processing, and multimedia production. This evolution brings both opportunities and risks. On the one hand, AI can enhance the design of information-hiding techniques and detect when these techniques are used; on the other hand, it introduces novel attack vectors and privacy challenges. For defensive purposes, AI models can detect fingerprints left by steganographic methods or monitor subtle variations in system parameters to expose covert channels that evade traditional defenses. Conversely, adversaries are leveraging AI for offensive strategies. Generative models can produce steganographic media that are statistically indistinguishable from benign content, while AI algorithms can uncover and optimize new side channels, enabling stealthy data exfiltration. This ``cat-and-mouse'' dynamics is a critical area of focus for the cybersecurity community.

Within this evolving context, ensuring the protection, integrity, and authenticity of information has become a central cybersecurity challenge. The widespread adoption of generative AI further amplifies the need for developing reliable mechanisms to watermark and trace digital content, including also ML models themselves.

The 1st Workshop on Hidden Information, Steganography, Privacy, and Emerging Risks is co-located with ITASEC & SERICS 2026, aims to bring together researchers and practitioners to explore cutting-edge developments in covert communications, digital watermarking, and steganography, with emphasis on the use of AI.