Colluding LoRA: A Compositional Vulnerability in LLM Safety Alignment
We show that safety alignment in modular LLMs can exhibit a compositional vulnerability: adapters that appear benign and plausibly functional in isolation can, when linearly composed, compromise safety. We study this failure mode through Colluding LoRA (CoLoRA), in which harmful behavior emerges only in the composition state. Unlike attacks that depend on adversarial prompts or explicit input triggers, this composition-triggered broad refusal suppression causes the model to comply with harmful requests under standard prompts once a particular set of adapters is loaded. This behavior exposes a combinatorial blind spot in current unit-centric defenses, for which exhaustive verification over adapter compositions is computationally intractable. Across several open-weight LLMs, we find that individual adapters remain benign in isolation while their composition yields high attack success rates, indicating that securing modular LLM supply-chains requires moving beyond single-module verification toward composition-aware defenses.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filte…
Safety AlignmentGeometric Data Perturbation with Noisy-Anchor Alignment for Privacy-Preserving Collaborative Learning
Geometric Data Perturbation (GDP) enables one-shot, privacy-preserving collaborative learning: each participant applies a distance-preserving transformation to its private data and uploads only the resulting representati…
When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models
Text-to-image (T2I) models are increasingly optimized for following user instructions faithfully. However, we find that this capability introduces a safety vulnerability we call Multi-Concept Compositional Unsafety (MCCU…
MOSAIC: Composable Safety Alignment with Modular Control Tokens
Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require context-dependent safety rules that vary acro…
Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories
Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs. Recent work attributes this to shallow safety, where alignment concentrates…