The paper introduces DiffusionHijack, a supply-chain backdoor attack that compromises the PRNG used by diffusion models to deterministically control generated images, which is successfully mitigated b…

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying Pseudo-Random Number Generator (PRNG) without altering the g…

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying PRNG, thereby amplifying the watermark without altering the…

This paper introduces HIJACKKV, the first attack framework to exploit the new threat of KV Cache Hijacking in large language models, achieving an average success rate of 94%.

The paper introduces DeCNIP, a method for identifying and neutralizing backdoors in large language models using representational analysis and neuron isolation pruning.

The paper introduces FlipGuard, a proactive defense framework against Quantization-Conditioned Backdoor (QCB) attacks in Large Language Models (LLMs), achieving high security with negligible performan…

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…

This paper proposes a density-aware attack that constructs triggers by placing poisoned samples in low-density regions of the clean data distribution, achieving high attack success rates even after st…

The paper introduces BadDLM, a unified framework that demonstrates a new class of backdoor vulnerabilities in Diffusion Language Models (DLMs) by exploiting their forward masking process across divers…

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 Two-stage Backdoor Hijacking (TSBH) to create persistent, trigger-activated malicious behaviors by manipulating the observable Chain-of-Thought (CoT) process in Large Language Model…

The paper proposes a unified, information-theoretic framework using universal hash functions to solve the bootstrapping of seedless QRNGs and to securely combine PQC and QKD keys against quantum adver…

QML-PipeGuard introduces a contract-based framework that monitors the behavioral fingerprint of quantum machine learning pipelines to detect both hardware drift and malicious channel substitution.

The paper introduces a software platform for generating and analyzing pseudo-random sequences (like LFSR and Mersenne Twister), demonstrating that while these classical generators are efficient, quant…

The paper proposes TimeGuard, a novel channel-wise pool training defense, to significantly improve the robustness of time series forecasting against backdoor attacks by addressing signal dilution and…

This paper demonstrates a novel attack against the shuffling defense used in secure Transformer inference, showing that randomly permuted activations can still be exploited to recover model weights.

This paper provides a comprehensive, system-level taxonomy for designing quantum-resistant network architectures, moving beyond simple protocol substitutions to address key distribution and management…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…