Language Model Security Database

An adversarial fine-tuning vulnerability exists in LLMs protected by text-based safety classifiers (such as Anthropic's Constitutional Classifiers). By utilizing a two-stage curriculum learning combined with hybrid RL+SFT (GRPO), an attacker can fine-tune a model to communicate using a minimal substitution cipher (replacing only 7-8 high-frequency characters) disguised within benign technical templates (e.g., forensic logs with 0x prefixes). This "Trojan-Speak" methodology bypasses text-level…

A malicious finetuning vulnerability exists in Large Language Models (LLMs) that process zero-width Unicode characters. An attacker can bypass training-data moderation filters and inference-time safety guardrails by finetuning the model to decode and encode invisible-character steganography. By injecting target malicious interactions encoded in a base-4 representation of zero-width characters alongside benign plaintext cover text during supervised finetuning (SFT), the model learns to process…

LLM agents equipped with tool-use, persistent memory, and environmental interaction capabilities are vulnerable to long-horizon attacks. Attackers can bypass single-turn safety guardrails by exploiting the temporal dimension of multi-turn interactions to incrementally steer agent behavior. The vulnerability manifests because the agent's safety mechanisms perform localized, single-step evaluations but fail to maintain semantic safety across extended interaction trajectories. This enables…

Large Language Model (LLM) fine-tuning interfaces are vulnerable to a semantic obfuscation attack that bypasses multi-stage safety defenses, including pre-upload data filtering, defensive fine-tuning algorithms, and post-training safety audits. The vulnerability exploits a "self-auditing" flaw where the provider uses the target model (or a similar variant) to screen training data. Attackers can submit a small dataset (approx. 500 samples) where harmful answers are obfuscated using a…

The Virus attack method enables attackers to bypass guardrail moderation on fine-tuning data, leading to a significant degradation of safety alignment in large language models (LLMs). This is achieved through a dual-objective data optimization strategy that crafts harmful data undetectable by the guardrail while maximizing their effectiveness in compromising the victim model's safety.