Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

Unified autoregressive models UAMs are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new...

Backdooring Masked Diffusion Language Models

Masked diffusion language models MDLMs are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs...

PT-2026-41691

Name of the Vulnerable Software and Affected Versions mcp-security versions prior to 0.1.9 Description The mcp-security framework fails to implement mandatory Server-Side Request Forgery SSRF mitigations—a flaw where an attacker can induce the server to make requests to an unintended location—as...

DOM Component Security Bypass

Vulnerability of the DOM component: The security of Mozilla Firefox, Firefox ESR, and the email client Thunderbird relies on bypassing authentication using an alternative path or channel. Exploiting this vulnerability allows a malicious actor to circumvent existing security restrictions remotely...

Be Kind, Rewrite: Benign Projections Via Rewriting Defend against LLM Data Poisoning Attacks

Large language models LLMs are highly susceptible to backdoor attacks BAs, wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM...

Federated Naive Bayes with Real Mixture of Gaussians and Institutional Governance Regularization for Network Intrusion Detection

Federated learning for intrusion detection rests on a flawed premise: that every participating institution contributes equally to the shared model. In practice, a financial institution with mature security controls and low vulnerability exposure produces fundamentally different data than a...

Agent Security Is a Systems Problem

We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness the dominant viewpoint...

MINI-MF76-R8GR-FPG4

Bulletin has no description...

CVE-2026-8755

A flaw has been found in fishaudio Bert-VITS2 up to 8f7fbd8c4770965225d258db548da27dc8dd934c. The affected element is the function getallmodels of the file hiyoriUI.py of the component Model Handler. This manipulation causes path traversal. The attack can be initiated remotely. The exploit has be...

EUVD-2026-30701

A flaw has been found in fishaudio Bert-VITS2 up to 8f7fbd8c4770965225d258db548da27dc8dd934c. The affected element is the function getallmodels of the file hiyoriUI.py of the component Model Handler. This manipulation causes path traversal. The attack can be initiated remotely. The exploit has be...

CVE-2026-8755

A flaw has been found in fishaudio Bert-VITS2 up to 8f7fbd8c4770965225d258db548da27dc8dd934c. The affected element is the function getallmodels of the file hiyoriUI.py of the component Model Handler. This manipulation causes path traversal. The attack can be initiated remotely. The exploit has be...

CVE-2026-8755 fishaudio Bert-VITS2 Model hiyoriUI.py _get_all_models path traversal

A flaw has been found in fishaudio Bert-VITS2 up to 8f7fbd8c4770965225d258db548da27dc8dd934c. The affected element is the function getallmodels of the file hiyoriUI.py of the component Model Handler. This manipulation causes path traversal. The attack can be initiated remotely. The exploit has be...

MINI-X499-27MW-4G89

Bulletin has no description...

MINI-G4CV-R6PF-35MQ

Bulletin has no description...

MINI-545H-9F2C-XJ2X

Bulletin has no description...

CVE-2026-8751

Affected software: h2oai h2o-3 (versions before 7402). The issue lies in the JAR Handler component, specifically the importBinaryModel() function in h2o-core/src/main/java/hex/Model.java, where input manipulation can trigger deserialization. This enables remote exploitation, with the exploit publ...

CVE-2026-8751 h2oai h2o-3 JAR Model.java importBinaryModel deserialization

A security flaw has been discovered in h2oai h2o-3 up to 7402. This affects the function importBinaryModel of the file h2o-core/src/main/java/hex/Model.java of the component JAR Handler. Performing a manipulation results in deserialization. The attack is possible to be carried out remotely. The...

EUVD-2026-30697

A security flaw has been discovered in h2oai h2o-3 up to 7402. This affects the function importBinaryModel of the file h2o-core/src/main/java/hex/Model.java of the component JAR Handler. Performing a manipulation results in deserialization. The attack is possible to be carried out remotely. The...

PT-2026-41566

Name of the Vulnerable Software and Affected Versions fishaudio Bert-VITS2 versions prior to 8f7fbd8c4770965225d258db548da27dc8dd934c Description A path traversal flaw exists in the Model Handler component, specifically within the get all models function of the hiyoriUI.py file. This issue allows...

Bert-VITS2 path traversal vulnerability

Bert-VITS2 is a core text-to-speech model developed by Fish Audio. Bert-VITS2 has a path traversal vulnerability, which stems from the getallmodels function in the hiyoriUI.py file within the Model Handler component. Attackers could potentially exploit this vulnerability remotely...