CORTEXA
← Browse
arxivcs.CRcs.LG2026-06-27

FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks

Aoying Zheng, Anqi Du, Zizhuang Deng, Yuxuan Chen

Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks. In these attacks, malicious behaviors remain dormant in full-precision models and activate only after specific quantization distortions, bypassing standard security audits. To mitigate this, we introduce FlipGuard, a proactive defense framework that selectively perturbs model weights prior to quantization. By breaking the adversary's precise alignment between weight patterns and quantization boundaries, FlipGuard suppresses backdoor activation without requiring access to training data or trigger samples. We further propose the Defense Effectiveness Ratio (DER), a unified metric to jointly evaluate security gains, utility preservation, and computational cost. Extensive experiments across seven LLMs (including StarCoder and LLaMA-family models) and three quantization schemes (INT8, FP4, NF4) demonstrate that FlipGuard effectively neutralizes QCBs across three scenarios, i.e., vulnerable code generation, content injection, and over-refusal, achieving high security with negligible performance degradation.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CLcs.CR2026-07-23

Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models

Shoya Otsu, Kei Suzuki, Toshiaki Koike-Akino, Jing Liu, Ye Wang

Advanced Persistent Threats (APTs) remain difficult to detect because only a small fraction of events in large-scale logs are attack-related, and investigation is expensive and hard to scale. Prior machine-learning approaches can reduce analyst workload, but they often rely on he…

View free PDFSource page
arxivcs.CRcs.LG2026-07-23

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification

Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova, Akira Takahashi, Antigoni Polychroniadou, Nicolas Papernot

Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data. This makes them especially attractive for auditing models deployed in sensitive domains such as…

View free PDFSource page
arxivcs.CRcs.AIcs.LG2026-07-22

Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection

Shrinidhi Sridhar, Vikas K. Malviya

An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices. But there is a trade-off between security and energy use, as strong detection models can drain the battery of devices fast. This work tests different Multi-Layer Pe…

View free PDFSource page
arxivcs.CRcs.CLcs.LG2026-07-23

Adversarial Prompts for Acceptance Collapse in Speculative Decoding

Run Wang, Chaoyi Zhou, Xi Liu, Yi Zhu, Amir Salarpour, Pedram MohajerAnsari, et al.

Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model. However, this guarantee of semantic equivalence masks a severe operational vulnerability: draft-targ…

View free PDFSource page
arxivcs.LGcs.ARcs.CR2026-07-26

ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection At Scale

Yaroslav Popryho, Debjit Pal, Inna Partin-Vaisband

Modern System-on-Chip (SoCs) often contain hundreds of millions to tens of billions of gates, making existing Hardware Trojan (HT) detection methods impractical due to their immense scale. The proposed approach incorporates symbolically enabled learning by modeling flattened gate…

View free PDFSource page