Whose Narrative Is It Anyway? A KV Cache Manipulation Attack

The Key ValueKV cache is an important component for efficient inference in autoregressive Large Language Models LLMs, but its role as a representation of the model's internal state makes it a potential target for integrity attacks. This paper introduces "History Swapping," a novel block-level...

Rethinking Denial-Of-Service: a Conditional Taxonomy Unifying Availability and Sustainability Threats

This paper proposes a unified, condition-based framework for classifying both legacy and cloud-era denial-of-service DoS attacks. The framework comprises three interrelated models: a formal conditional tree taxonomy, a hierarchical lattice structure based on order theory, and a conceptual Venn...

CAVGAN: Unifying Jailbreak and Defense of LLMs Via Generative Adversarial Attacks on Their Internal Representations

Security alignment enables the Large Language Model LLM to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM jailbreak attacks and defenses. We analyze the security protection...

CVE-2022-26024

Improper access control in the IntelR NUC HDMI Firmware Update Tool for NUC7i3DN, NUC7i5DN and NUC7i7DN before version 1.78.2.0.7 may allow an authenticated user to potentially enable escalation of privilege via local access...

PT-2022-18168 · Arris · Sbr-Ac1900P +2

Name of the Vulnerable Software and Affected Versions: Arris routers SBR-AC1900P version 1.0.7-B05 Arris routers SBR-AC3200P version 1.0.7-B05 Arris routers SBR-AC1200P version 1.0.5-B05 Description: A command injection issue was discovered in the ddns function of the affected Arris routers. This...