Pith. sign in

REVIEW 13 cited by

Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.02949 v1 pith:JHMHFF5R submitted 2023-10-04 cs.CL cs.AIcs.CRcs.LG

classification cs.CLcs.AIcs.CRcs.LG
keywords modelsattackshadowalignmentharmfullanguagellmsmalicious
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the essential cost of data annotation and computation. To ensure AI safety, extensive safety-alignment measures have been conducted to armor these models against malicious use (primarily hard prompt attack). However, beneath the seemingly resilient facade of the armor, there might lurk a shadow. By simply tuning on 100 malicious examples with 1 GPU hour, these safely aligned LLMs can be easily subverted to generate harmful content. Formally, we term a new attack as Shadow Alignment: utilizing a tiny amount of data can elicit safely-aligned models to adapt to harmful tasks without sacrificing model helpfulness. Remarkably, the subverted models retain their capability to respond appropriately to regular inquiries. Experiments across 8 models released by 5 different organizations (LLaMa-2, Falcon, InternLM, BaiChuan2, Vicuna) demonstrate the effectiveness of shadow alignment attack. Besides, the single-turn English-only attack successfully transfers to multi-turn dialogue and other languages. This study serves as a clarion call for a collective effort to overhaul and fortify the safety of open-source LLMs against malicious attackers.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm

    cs.CR 2025-09 conditional novelty 7.0 of 10

    A trigger-tag watermark embedded by fine-tuning lets modified LLMs mark their own phishing outputs for cheap detection.

  2. Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs

    cs.CR 2025-09 unverdicted novelty 7.0 of 10

    TRIAL, a multi-turn jailbreak method that frames harmful actions as lesser-evil ethical choices, reports high jailbreak success rates across open and closed LLMs.

  3. How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Task adaptation with SFT drifts LLM alignment substantially more than RLVR, and the drift shows up both in behavior and in internal representations.

  4. Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Domain-specific abliteration removes cybersecurity refusal on Kimi K2 (100%→7%) while preserving most other safety refusals; susceptibility depends mainly on safety-training method and architecture, not size.

  5. TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment

    cs.LG 2026-06 conditional novelty 6.0 of 10

    One low-rank adapter, trained across simulated harmful fine-tuning trajectories, restores ≥94% safety on fine-tuned LLMs while keeping task accuracy within ±1.7% of the undefended model.

  6. Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs

    cs.AI 2025-11 conditional novelty 6.0 of 10

    Benign PEFT fine-tuning changes LLM safety and fairness: adapter-based methods (LoRA, IA3) preserve alignment better than prompt-based methods, and the base model strongly moderates outcomes.

  7. Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Vulnerability-Aware Alignment splits safety training data into fragile and robust groups, then uses group robust optimization and adversarial perturbations, cutting harmful response rates after harmful fine-tuning by ...

  8. Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

    cs.CL 2025-08 conditional novelty 5.0 of 10

    ROSI bakes the refusal direction into a model's weight matrices via a rank-one update, raising refusal and jailbreak robustness with minimal measured utility cost.

  9. S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner

    cs.AI 2025-08 conditional novelty 5.0 of 10

    S3LoRA prunes LoRA layers with the sharpest spectral update concentration to improve safety in fine-tuned LLM agents without needing base models or extra data.

  10. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

    cs.CL 2025-08 reject novelty 5.0 of 10

    Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.

  11. Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models

    cs.CL 2025-07 conditional novelty 5.0 of 10

    The paper reports higher harmful-output rates in three open-source VLMs from detailed image descriptions, in-context examples, and positive openings, and from a skip connection between internal layers, with memes riva...

  12. SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models

    cs.CR 2025-06 conditional novelty 4.0 of 10

    Across 510 HarmBench behaviors and seven attack methods, GPT-4 models show more consistent jailbreak resilience than DeepSeek models, whose vulnerability grows with scale.

  13. Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Fine-tuning small LLMs on benign data raises harmfulness scores, but those scores vary widely across random seeds, temperatures, and repeated runs, making single-run safety comparisons unreliable.

Pith tools