The paper introduces AIM, a two‑stage approach for unlearning identity‑specific information from multimodal large language models (MLLMs) when retain images are not available at deletion time. AIM first anchors an identity‑forgetting target using a universal visual prompt, then aligns the vision encoder to this target under a Fisher‑based constraint. Experiments demonstrate that AIM effectively removes identity knowledge while preserving other visual perception capabilities and prior knowledge.
arXiv:2608.30649v1 Announce Type: new Abstract: Removing a specific individual's information from multimodal large language models (MLLMs) is often needed after deployment, but existing methods rely...
arXiv:2511. 20196v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training.
The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while pre...
arXiv:2610.01962v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of...
arXiv:2608.01008v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowle...
ICM-Bench is a new benchmark for evaluating identity-centric reasoning in multimodal agents with long-term memory. It consists of 839 synthetic video clips totaling 141 minutes and 1,217 open-ended questions about six recurring adults in a one-year life album. The benchmark isolates the ability to maintain recurring person identities and reason over their cross-time relations, and compares various baseline systems, showing that while Gemini 3.1 Pro performs well overall, its accuracy drops on questions requiring long-term identity profiles.
Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora. Removing such knowledge is essential for building trustworthy AI systems.
arXiv:2608. 03791v1 Announce Type: new Abstract: Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora.
arXiv:2605.22311v2 Announce Type: replace Abstract: Identity-conditioned diffusion models enable high-quality and identity-consistent face generation, but they also raise severe privacy concerns, as...
The paper introduces Anti-Persona, an image-level defense that prevents unauthorized identity binding and recognition in personalized vision–language models. By aggregating visual features from multiple reference images into an identity prototype and applying subtle perturbations, the method disrupts prototype alignment in the vision‑encoder space while maintaining visual fidelity. Experiments on two personalized LVLMs show protection rates up to 95.0% and robustness across prompt variations and encoder mismatches.
The paper introduces "open‑set adversarial forgetting" to make selected identities unlinkable in face recognition models while keeping the system functional for other users. Three loss functions are proposed: one disperses embeddings from their centroid, and two map each image to a near‑orthogonal target—either learned via the classifier head or fixed as an almost‑orthonormal frame. Experiments on multiple backbones and forget scales show that these losses, especially the orthonormal‑frame approach, effectively render the targeted identities unidentifiable and outperform prior methods while preserving higher retain rates.
arXiv:2604.03114v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) may need to forget visual concepts after deployment because of privacy, copyright, licensing, safety, or policy...