6 papers
DUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent Security
Ivan Aleksandrov, German Kochnev, Sabrina Sadiekh +1
LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume passive users and static con…
HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation
Nikita Oblakov, Sabrina Sadiekh, Evgeniy Kokuykin
Production LLMs must handle inputs that attempt to override system instructions, bypass safety policies or elicit harmful responses. A common mitigation is a separate guardrail mod…
GLiNER Guard: Unified Encoder Family for Production LLM Safety and Privacy
Bogdan Minko, Sabrina Sadiekh, Evgeniy Kokuykin
Production LLM systems require both safety moderation and PII detection under strict latency and cost constraints. This creates a trade-off: autoregressive moderators are accurate…
Cross-Lingual Jailbreak Detection via Semantic Codebooks
Shirin Alanova, Bogdan Minko, Sabrina Sadiekh +1
Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that trans…
Towards Understanding the Robustness of Sparse Autoencoders
Ahson Saiyed, Sabrina Sadiekh, Chirag Agarwal
Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used fo…
Polarity-Aware Probing for Quantifying Latent Alignment in Language Models
Sabrina Sadiekh, Elena Ericheva, Chirag Agarwal
Advances in unsupervised probes such as Contrast-Consistent Search (CCS), which reveal latent beliefs without relying on token outputs, raise the question of whether these methods…