IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis

• URL: http://arxiv.org/abs/2603.15679v1
• Date: Sat, 14 Mar 2026 08:38:47 GMT
• Title: IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
• Abstract summary: Our work builds on the principle that security should be as context-aware as the threat itself, intrinsically bound to the personalized concept.<n>We present IDENTITYGUARD, which realizes this principle through a conditional restriction that blocks harmful content only when combined with the personalized identity.<n> Experiments show our approach prevents misuse while preserving the model's utility and enabling robust traceability.
• Score: 11.116425897665058
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The nature of personalized text-to-image models poses a unique safety challenge that generic context-blind methods are ill-equipped to handle. Such global filters create a dilemma: to prevent misuse, they are forced to damage the model's broader utility by erasing concepts entirely, causing unacceptable collateral damage.Our work presents a more precisely targeted approach, built on the principle that security should be as context-aware as the threat itself, intrinsically bound to the personalized concept. We present IDENTITYGUARD, which realizes this principle through a conditional restriction that blocks harmful content only when combined with the personalized identity, and a concept-specific watermark for precise traceability. Experiments show our approach prevents misuse while preserving the model's utility and enabling robust traceability. By moving beyond blunt, global filters, our work demonstrates a more effective and responsible path toward AI safety.

Related papers

• Introspective Attention Modulation for Safe Text-to-Image Generation [37.67434449197168]
  State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content.<n>We introduce a unique approach that achieves safety by regulating the model's attention dynamics through inference-time introspection.
  arXiv  Detail & Related papers  (2026-07-16T12:53:45Z)
• When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents [49.341830745910194]
  In this paper, we reveal intent legitimation, a previously underexplored safety failure in personalized agents.<n>Our work provides the first systematic exploration and evaluation of intent legitimation as a safety failure mode.
  arXiv  Detail & Related papers  (2026-01-25T15:42:01Z)
• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models [67.84174763413178]
  We introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection.<n>We show that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks.
  arXiv  Detail & Related papers  (2026-01-13T15:01:38Z)
• Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation [74.5813283875938]
  Zero-shot image-to-image generation poses substantial risks related to intellectual property violations.<n>This work presents Adapter Shield, the first universal and authentication-integrated solution aimed at defending personal images from misuse.<n>Our method surpasses existing state-of-the-art defenses in blocking unauthorized zero-shot image synthesis.
  arXiv  Detail & Related papers  (2025-11-25T04:49:16Z)
• Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation [26.890796322896346]
  Defense mechanisms like Anti-DreamBooth attempt to mitigate the risk of facial identity leakage.<n>We identify two critical yet overlooked limitations of these methods.<n>Results reveal that none of the current methods maintains their protective effectiveness under such threats.
  arXiv  Detail & Related papers  (2025-11-13T14:56:25Z)
• SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models [74.11062256255387]
  Text-to-image models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce harmful content.<n>We introduce SafeGuider, a two-step framework designed for robust safety control without compromising generation quality.<n>SafeGuider demonstrates exceptional effectiveness in minimizing attack success rates, achieving a maximum rate of only 5.48% across various attack scenarios.
  arXiv  Detail & Related papers  (2025-10-05T10:24:48Z)
• GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention [5.429335132446078]
  GIFT: a Gradient-aware Immunization technique to defend diffusion models against malicious Fine-Tuning.
  arXiv  Detail & Related papers  (2025-07-18T01:47:07Z)
• CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models [7.68494752148263]
  CURE is a training-free concept unlearning framework that operates directly in the weight space of pre-trained diffusion models.<n>The Spectral Eraser identifies and isolates features unique to the undesired concept while preserving safe attributes.<n>CURE achieves a more efficient and thorough removal for targeted artistic styles, objects, identities, or explicit content.
  arXiv  Detail & Related papers  (2025-05-19T03:53:06Z)
• TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models [53.937498564603054]
  Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images.<n>To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts.<n>We propose TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation.
  arXiv  Detail & Related papers  (2025-03-10T14:37:53Z)
• Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction [88.18235230849554]
  Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs.<n>We leverage safe embeddings and a modified diffusion process with weighted tunable summation in the latent space to generate safer images.<n>We identify trade-offs between safety and censorship, which presents a necessary perspective in the development of ethical AI models.
  arXiv  Detail & Related papers  (2024-11-21T09:47:13Z)
• Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models? [52.238883592674696]
  Ring-A-Bell is a model-agnostic red-teaming tool for T2I diffusion models. It identifies problematic prompts for diffusion models with the corresponding generation of inappropriate content. Our results show that Ring-A-Bell, by manipulating safe prompting benchmarks, can transform prompts that were originally regarded as safe to evade existing safety mechanisms.
  arXiv  Detail & Related papers  (2023-10-16T02:11:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.