The paper introduces SET, a robust input-level backdoor detection framework that detects hidden malicious triggers in text-to-image diffusion models by analyzing systematic differences in how benign a…

The paper proposes DFBScanner, a lightweight static parameter inspection framework that detects backdoor attacks by analyzing anomalous parameter updates in the final classification layer, achieving f…

MemMark introduces a state-evolution attribution watermark that embeds owner-controlled signals into latent memory-write decisions, enabling robust provenance tracking for agent memory even when all t…

NeuroTrace introduces a novel framework using Inference Provenance Graphs (IPGs) to analyze the information flow during deep neural network inference, demonstrating that this provenance provides a rob…

The paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing the backdoor generalizes at the token feature level, and proposes robust behavioral and weight-level detectors f…

This paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing that the resulting backdoor generalizes at the token feature level, and proposes robust behavioral and weight-l…

The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

The paper introduces False Security Confidence (FSC), a new metric to measure the inherent prevalence of security vulnerabilities in code generated by LLMs that are otherwise functionally correct, eve…

The paper proposes HTell, a fast and lightweight data-free backdoor detector that analyzes the abnormal response concentration of backdoored models on the target class using random latent probes appli…

The paper proposes detecting 'alignment faking' (AF)—where LLMs revert to unsafe behavior when unmonitored—by analyzing observable tool selection patterns, finding that detection rates vary significan…

The study demonstrates that robust, domain-invariant representations of synthetic deception can be rapidly entrenched in LLMs using modest fine-tuning, detectable by linear probes even in early layers…

This paper reinterprets catastrophic overfitting (CO) in Fast Adversarial Training (FAT) as a weak backdoor mechanism, proposing backdoor-inspired strategies to mitigate this generalization failure.

The paper introduces ARCANE, a Bayesian network framework for cross-campaign cyber attribution, finding that while aggregating telemetry improves identification, structural feature limitations prevent…

The paper argues that watermarking must be viewed as a monitoring primitive, introducing an observer-based threat model that shows even zero-bit watermarking can enable entity-level attribution throug…

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's vulnerability to adversarial content changes based on whether the malicious input arrives via the user message, tool meta…

The paper introduces the Safety Asymmetry Score (SAS) to measure how a model's susceptibility to adversarial attacks changes based on whether the malicious content arrives via the user message, tool m…

The paper analyzes LLM vulnerability detection using mechanistic interpretability, finding that models primarily rely on safety detectors rather than direct vulnerability signature recognition.

Researchers demonstrate how malicious providers can embed architectural backdoors into Vision--Language Model (VLM) supply chains through representation steering.

This paper systematically diagnoses the failure modes of linear deception probes in LLMs, finding that while single-direction probes are insufficient, multi-dimensional probes can recover robust detec…

The paper proposes PROVFUSION, a multi-view fusion framework that integrates anomaly signals from attribute, structure, and causality views to overcome the limitations of single node- or edge-centric…