# The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness

arXiv: https://arxiv.org/abs/2401.00287 · HTML: https://mlsanity.com/paper/2401.00287/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 56 references that are in the map.
- First posted on arXiv 30 Dec 2023.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked](https://mlsanity.com/paper/2308.07308/) (2023)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs](https://mlsanity.com/paper/2308.13387/) (2023)
- [Attack Prompt Generation for Red Teaming and Defending Large Language Models](https://mlsanity.com/paper/2310.12505/) (2023)
- [Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings](https://mlsanity.com/paper/2203.00211/) (2022)
- [Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models](https://mlsanity.com/paper/2307.08487/) (2023)
- [Bypassing the Safety Training of Open-Source LLMs with Priming Attacks](https://mlsanity.com/paper/2312.12321/) (2023)
- [How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities](https://mlsanity.com/paper/2311.09447/) (2023)
- [Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information](https://mlsanity.com/paper/2311.11509/) (2023)

## Built on by (most cited first, 30 of 67)

- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://mlsanity.com/paper/2501.09004/) (2025)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes](https://mlsanity.com/paper/2403.00867/) (2024)
- [JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models](https://mlsanity.com/paper/2407.01599/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training](https://mlsanity.com/paper/2508.09224/) (2025)
- [SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering](https://mlsanity.com/paper/2408.11491/) (2024)
- [A Theoretical Understanding of Self-Correction through In-context Alignment](https://mlsanity.com/paper/2405.18634/) (2024)
- [Boosting Jailbreak Attack with Momentum](https://mlsanity.com/paper/2405.01229/) (2024)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models](https://mlsanity.com/paper/2409.00598/) (2024)
- [ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings](https://mlsanity.com/paper/2402.16006/) (2024)
- [Defending Jailbreak Prompts via In-Context Adversarial Game](https://mlsanity.com/paper/2402.13148/) (2024)
- [The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs](https://mlsanity.com/paper/2506.11094/) (2025)
- [Prompt Leakage effect and defense strategies for multi-turn LLM interactions](https://mlsanity.com/paper/2404.16251/) (2024)
- [X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability](https://mlsanity.com/paper/2502.09990/) (2025)
- [Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions](https://mlsanity.com/paper/2504.11373/) (2025)
- [Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery](https://mlsanity.com/paper/2504.01205/) (2025)
- [SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression](https://mlsanity.com/paper/2506.12707/) (2025)
- [GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation](https://mlsanity.com/paper/2502.05911/) (2025)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem](https://mlsanity.com/paper/2506.15170/) (2025)
- [Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection](https://mlsanity.com/paper/2510.01270/) (2025)
- [Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies](https://mlsanity.com/paper/2406.03827/) (2024)
- [PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing](https://mlsanity.com/paper/2407.16318/) (2024)
- [Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs](https://mlsanity.com/paper/2502.19041/) (2025)
- [LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures](https://mlsanity.com/paper/2505.01177/) (2025)
- [When to Speak, When to Abstain: Contrastive Decoding with Abstention](https://mlsanity.com/paper/2412.12527/) (2024)
- [PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization](https://mlsanity.com/paper/2504.01444/) (2025)

## Abstract (arXiv)

As Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications, their safety concerns become critical areas of NLP research. This paper presents Safety and Over-Defensiveness Evaluation (SODE) benchmark: a collection of diverse safe and unsafe prompts with carefully designed evaluation methods that facilitate systematic evaluation, comparison, and analysis over 'safety' and 'over-defensiveness.' With SODE, we study a variety of LLM defense strategies over multiple state-of-the-art LLMs, which reveals several interesting and important findings, such as (a) the widely popular 'self-checking' techniques indeed improve the safety against unsafe inputs, but this comes at the cost of extreme over-defensiveness on the safe inputs, (b) providing a safety instruction along with in-context exemplars (of both safe and unsafe inputs) consistently improves safety and also mitigates undue over-defensiveness of the models, (c) providing contextual knowledge easily breaks the safety guardrails and makes the models more vulnerable to generating unsafe responses. Overall, our work reveals numerous such critical findings that we believe will pave the way and facilitate further research in improving the safety of LLMs.