The Structural Safety Generalization Problem (2025.findings-acl)

Copied to clipboard

Challenge: LLM jailbreaks are a widespread safety challenge.
Approach: They propose a structure-rewriting guardrail that allows for more efficient safety assessment . single-turn attacks are the most extensively explored in the literature .
Outcome: The proposed framework can be used to enable new defenses, the authors show . they show that the proposed framework reduces the risk of harmful inputs .

Similar Papers

LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing security guardrails built from static datasets ignore each model’s unique safety profile and often force trade-offs between safety and utility.
Approach: They propose a framework for learning model-specific guardrails tailored to each LLM’s vulnerabilities.
Outcome: The proposed framework significantly outperforms baseline guardrails on multiple real-world LLMs, achieving superior robustness, adaptability, and generalization.
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models exhibit remarkable generative capabilities but can be misused for harmful purposes.
Approach: They propose a framework that transforms natural language inputs into code inputs.
Outcome: The proposed framework bypasses the safety guardrails of all models more than 80% of the time.
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in natural language processing tasks but are vulnerable to harmful content and being exploited for malicious purposes.
Approach: They propose a framework to measure the risk coverage of alignment datasets across three dimensions: Lexical Diversity, Malicious Intent, and Jailbreak Tactics.
Outcome: The proposed framework measures risk coverage across Lexical Diversity, Malicious Intent, and Jailbreak Tactics.
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Existing safety evaluations of large language models aggregate harms under generic categories such as "Identity Hate" a bilingual benchmark identifies a selective safety trap, where defense rates vary by up to 42% within the same model solely based on the target group.
Approach: They propose a bilingual adversarial benchmark to audit selective safety in large language models . defense rates vary by up to 42% within the same model solely based on target group .
Outcome: The proposed benchmark identifies a selective safety trap in large language models . defense rates vary by up to 42% within the same model solely based on the target group.
Jailbreak Attack Initializations as Extractors of Compliance Directions (2025.findings-emnlp)

Copied to clipboard

Challenge: Safety-aligned LLMs respond to prompts with compliance or refusal, each corresponding to distinct directions in the model’s activation space.
Approach: They propose an initialization framework that aims to project unseen prompts further along compliance directions.
Outcome: The proposed initialization framework achieves an increased attack success rate and reduced computational overhead, highlighting the fragility of safety-aligned LLMs.
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race? (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies have focused on the models, neglecting the full deployment pipeline . previous studies have underestimated the practical success of these attacks .
Approach: They evaluate the effectiveness of jailbreak attacks targeting LLM safety alignment . they highlight critical gaps and call for further refinement of detection accuracy and usability .
Outcome: The proposed attacks can detect at least one safety filter across the entire deployment pipeline.
When Safety Alignment Fails to Generalize: Probing with Language Game Jailbreaks (2026.findings-acl)

Copied to clipboard

Challenge: Existing safety alignment methods rely on fixed or narrow transformation schemes to generalize . existing methods based on fixed and narrow transformations are often inadequate .
Approach: They propose a framework for discovering and refining language game-based jailbreaks to probe alignment generalization.
Outcome: The proposed framework allows controlled exploration of alignment behavior across closely related linguistic variants.
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment.
Approach: They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses.
Outcome: The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm.
When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models (2026.eacl-srw)

Copied to clipboard

Challenge: Existing safety evaluations rely on fixed collections of harmful prompts . such attacks span single-shot prompts, multi-turn interactions, cross-lingual settings .
Approach: They propose to use black-box prompt optimization techniques to search for safety failures . they use GPT-5.1 to optimize for a continuous danger score .
Outcome: The proposed approach reduces effective safeguards for large language models . the average danger score of Qwen 3 8B increases from 0.09 in its baseline setting to 0.79 after optimization.
X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for enhancing LLM security compromise usability, study finds . boundary-safe representations close to harmful representations are disrupted, resulting in usability decline .
Approach: They propose a method to push harmful representations away from boundary-safe representations and obtain an exact distinction boundary.
Outcome: The proposed method reduces over-refusal rate and maintains general capability . it pushes harmful representations away from boundary-safe representations, thereby reducing usability.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations