Multimodal models
Models that read or produce images, audio or video, and attacks that hide inside those inputs.
- All items
- 30
- Last 90 days
- 19
- Change
- +375%vs 4 before
Items per month
| Month | Items |
|---|---|
| Jun 2025 | 0 |
| Jul 2025 | 0 |
| Aug 2025 | 0 |
| Sep 2025 | 0 |
| Oct 2025 | 0 |
| Nov 2025 | 0 |
| Dec 2025 | 0 |
| Jan 2026 | 1 |
| Feb 2026 | 1 |
| Mar 2026 | 2 |
| Apr 2026 | 2 |
| May 2026 | 1 |
| Jun 2026 | 2 |
| Jul 2026 | 1 |
| Aug 2026 | 1 |
| Sep 2026 | 4 |
| Oct 2026 | 13 |
| Nov 2026 | 2 |
30 items
ThreatsDay: Android Spyware, PLC Attacks, AI Image Prompt Injection + 12 More Stories
Jul 23, 2026MediumNewsSecurityResearchGitHub will begin rejecting command-line support bundle uploads from older GHES appliances starting August 18, 2026, unless they are patched. A separate npm package, @copilot-mcp/apex, acts as a postinstall dropper that installs a macOS infostealer, and a fake VS Code extension, "Markdown All Pro", impersonates Markdown All in One to beacon machine details and fetch remote payloads.
Fix: To avoid disruption when submitting support bundles, update your GHES instance to the latest patch release available for your current version line. At minimum, the required patch versions are: 3.21.3, 3.20.5, 3.19.9, 3.18.12, and 3.17.18.
The Hacker NewsEnhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
Jun 10, 2026InfoResearchPeer-reviewedSecurityResearchResearchers show that black-box targeted attacks on Large Vision-Language Models can be made more precise by working through the projector, a semantic bridge between vision and language. They propose Intermediate Projector Guided Attack (IPGA), which aligns Q-Former query outputs with a target and transfers across models, and IPGA with Residual Query Alignment (IPGA-R), which also preserves non-target content for fine-grained edits. The authors report that IPGA beats baselines on global attacks, IPGA-R wins on fine-grained attacks, and the method transfers to Google Gemini and OpenAI GPT.
IEEE Xplore (Security & AI Journals)Introducing Gemma 4 12B: a unified, encoder-free multimodal model
Jun 9, 2026InfoNewsIndustryResearchGoogle DeepMind introduced Gemma 4 12B, a mid-sized model with native audio inputs designed to run locally on laptops with 16GB of VRAM or unified memory. Its encoder-free architecture feeds vision and audio inputs directly into the LLM backbone, and the model is released under an Apache 2.0 license with Multi-Token Prediction drafters to reduce latency.
DeepMind Safety ResearchPVLM: Parsing-Aware Vision-Language Model With Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution
May 14, 2026InfoResearchPeer-reviewedSecurityResearchPVLM is a parsing-aware vision-language model with dynamic contrastive learning for zero-shot deepfake attribution, meaning it traces forged faces to generators not seen in training, including diffusion models. The authors build a fine-grained ZS-DFA benchmark and use face parsing to exploit differences in how GAN and diffusion generators preserve source facial attributes. They report that the model exceeds the state of the art on the ZS-DFA benchmark across various protocol evaluations.
IEEE Xplore (Security & AI Journals)Privacy-preserving for user-uploaded images and text in Vision-Language Models
Apr 28, 2026InfoResearchPeer-reviewedPrivacyResearchElsevier Security JournalsVLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
Apr 14, 2026InfoResearchPeer-reviewedResearchSafetyVLBiasBench is a benchmark for measuring social bias in Large Vision-Language Models (LVLMs). It covers nine bias categories plus two intersectional ones (race × gender and race × social economic status). The dataset has 128,342 samples built from 46,848 images generated with Stable Diffusion XL, and the authors evaluated 15 open-source models and two closed-source models.
IEEE Xplore (Security & AI Journals)SMInject: Specious Malignant Injection Attacks With Semantically-Enhanced Tokens in Cross-Modal Retrieval
Mar 13, 2026InfoResearchPeer-reviewedSecurityResearchSMInject is a new injection attack framework against pre-trained multimodal models used in cross-modal retrieval. It generates deceptive injections that combine concepts through causal correlation across modalities, and aligns them in the encoded embedding space to boost effectiveness. On representative multimodal models, it reportedly achieves over 14% higher attack success rate and 6% higher Hit@5 than state-of-the-art methods while preserving overall model utility.
IEEE Xplore (Security & AI Journals)Are Large Vision-Language Models Robust to Adversarial Visual Transformations?
Mar 5, 2026InfoResearchPeer-reviewedSecurityResearchResearchers assess how robust large vision-language models (LVLMs) are to adversarial visual transformations, a simpler attack style than optimizing perturbations or manipulating prompts. They test LVLM resilience across all possible transformation operations and find that combining the most harmful transformations yields more effective attacks. They also introduce adversarial learning of visual transformations, which applies malicious transformations to raw images via gradient approximation to improve attack effectiveness and imperceptibility.
IEEE Xplore (Security & AI Journals)Evaluating and Mitigating Relationship Hallucinations in Large Vision-Language Models
Feb 3, 2026InfoResearchPeer-reviewedResearchSafetyR-Bench is a new benchmark for measuring hallucinations about relationships between objects in Large Vision-Language Models, using image-level questions on whether a relationship exists and instance-level questions on local visual comprehension. The authors trace these hallucinations to relationship-relationship, subject-relationship and relationship-object co-occurrences, worsened by long-tail distributions in visual datasets. They report that region-level image-text alignment reduces them and propose a baseline, Region-Aware Alignment Mitigation (RA$^{2}$2M), that directs model attention to relevant regions.
Fix: Region-level image-text alignment helps mitigate relationship hallucinations; the authors propose RA$^{2}$2M (Region-Aware Alignment Mitigation) as a new baseline that enhances model attention to relevant regions.
IEEE Xplore (Security & AI Journals)NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
Jan 30, 2026InfoResearchPeer-reviewedSecurityResearchNAP-Tuning extends Adversarial Prompt Tuning (AdvPT) for vision-language models such as CLIP by adding a multi-modal, multi-layer prompting framework. Its core is a Neural Augmentor that uses TokenRefiners, lightweight modules that reconstruct purified features through residual connections to correct adversarial distortions in feature space. Under the AutoAttack benchmark it outperforms the strongest baselines by 32.3% on ViT-B16 and 31.3% on ViT-B32 while keeping competitive clean accuracy.
IEEE Xplore (Security & AI Journals)
Topic added 2026-10-09. An item belongs to this topic when its title matches one of the topic's patterns or its summary mentions the topic at least twice. Report a wrong match with the feedback button on the item.