This work introduces a novel approach, \textit{CanaryTrace}, to safeguard the ownership of text datasets and effectively detect unauthorized use by RA-LLMs, and demonstrates high query efficiency, detectability, and consistency, along with minimal perturbation to the original dataset, all without compromising the perfo...
Yepeng Liu, Xuandong Zhao, D. Song et al.· arXiv.org· 15 citations· ⚡1
This work introduces a clinically grounded framework that evaluates leakage along a graded axis of adversarial access, ranging from publicly inferable demographics to leaked note fragments, and provides a practical, reusable framework for contextual privacy evaluation of medical LMs.
Sasha Ronaghi, Sana Tonekaboni, Lena Stempfle et al.· arXiv.org· 0 citations
This work introduces AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents, and uncovers the Safe Source Paradox, a safety-utility trade-off for retrieval-enabled agents.
Aditya Nawal, Manit Baser, M. Gurusamy· arXiv.org· 0 citations
This work finds that jailbreak robustness is highly fragile to operational-state variation: even when the attack remains fixed, changing only an ordinary system prompt not designed to affect safety can dramatically alter attack success rates.
Yuna Park, Hwang Youn Kim, Yujin Kim et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
CIPR (Coding In Poisoned Repos), the first benchmark that systematically varies PLCs in poisoned real-world repositories, is introduced and highlights that coding agent vulnerability is not a static property, but a dynamic outcome shaped by everyday user configurations.
Fu-Kang Zhu, Bin-Bin Zhao, Rui-Xiao Lin et al.· 1 citation
Experiments across multiple datasets, victim models, and large language models show that OASIS consistently outperforms strong standalone baselines and simple manually constructed chains, suggesting that attacker composition is not merely an implementation choice, but a practical optimization target for improving hard-...
The survey aims to serve as both a reference and a roadmap for practical and responsible linguistic steganography in the LLM era by identifying five specific paradigm shifts in the LLM era.
Ruiyi Yan, Chenhui Chu, Zhong-Liang Yang et al.· 4 citations
This work proposes a four-phase protocol that enables the aggregation of xMK-CKKS over a shared wireless channel without channel estimation and shows that the residual noise induced by encryption and wireless aggregation preserves the standard convergence rate up to a negligible noise floor.
Anthony Ayli, K. Harris, J. Fahs et al.· arXiv.org· 0 citations
VeriX-Anon is a multi-layered verification framework for outsourced Target-Driven k-anonymization combining three orthogonal mechanisms: deterministic verification via Merkle-style hashing of an Authenticated Decision Tree, probabilistic verification via Boundary Sentinels and exact-duplicate Twins with cryptographic i...
Concerns are raised about the trustworthiness of ML training processes based on AV annotations and it is argued that further investigation is needed to develop more reliable labeling strategies.
Tianwei Lan, Luca Demetrio, F. Nait-Abdesselam et al.· IEEE Transactions on Informa...· 5 citations
This work proposes to use GFlowNet fine-tuning followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts, and finds that the attacks generated by the method are effective against a wide range of target LLMs, both with and without safety tuning, and transfer we...
Seanie Lee, Minsu Kim, Lynn Cherif et al.· International Conference on...· 62 citations· ⚡8
An attack is proposed, FAB (Finetuning-activated Adversarial Behaviors), which compromises an LLM via meta-learning techniques that simulate downstream finetuning, explicitly optimizing for the emergence of adversarial behaviors in the finetuned models.
Thibaud Gloaguen, Mark Vero, Robin Staab et al.· 4 citations
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Critical flaws, compromised release channels and agentic AI threats landed within days of each other in mid-October 2026. Why “Black October” may say more about how well we now find weaknesses than about the attacks themselves. The post Black October? The Week AI Changed the Cybersecurity Conversation appeared first on GPT-Lab.
