Pith. sign in

REVIEW 7 cited by

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

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 2309.14348 v3 pith:THMDJAID submitted 2023-09-18 cs.CL cs.AIcs.CRcs.LG

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

classification cs.CL cs.AIcs.CRcs.LG
keywords alignment-breakingattacksra-llmalignedllmspromptscontentdefend
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content. Though a line of research has focused on aligning LLMs with human values and preventing them from producing inappropriate content, such alignments are usually vulnerable and can be bypassed by alignment-breaking attacks via adversarially optimized or handcrafted jailbreaking prompts. In this work, we introduce a Robustly Aligned LLM (RA-LLM) to defend against potential alignment-breaking attacks. RA-LLM can be directly constructed upon an existing aligned LLM with a robust alignment checking function, without requiring any expensive retraining or fine-tuning process of the original LLM. Furthermore, we also provide a theoretical analysis for RA-LLM to verify its effectiveness in defending against alignment-breaking attacks. Through real-world experiments on open-source large language models, we demonstrate that RA-LLM can successfully defend against both state-of-the-art adversarial prompts and popular handcrafted jailbreaking prompts by reducing their attack success rates from nearly 100% to around 10% or less.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling

    cs.CR 2026-05 unverdicted novelty 6.0

    Ellipsoid Control is a white-list test-time jailbreak defense that fits an anisotropic ellipsoid from benign activations to constrain projected gradient descent updates, aiming to improve the safety-utility tradeoff o...

  2. ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

    cs.CR 2026-04 unverdicted novelty 6.0

    ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.

  3. Learning from Mistakes: Can LLM Self-Recover after Misalignment?

    cs.CY 2026-03 conditional novelty 6.0

    LLMs sometimes regain safe behavior after multi-turn jailbreaks, and this recovery can be measured with turn-level safety trajectories and metrics such as misalignment length and recovery duration.

  4. ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments

    cs.CL 2025-08 unverdicted novelty 6.0

    ReasoningGuard is an inference-time method that uses attention mechanisms to inject safety aha moments and scaling sampling to defend large reasoning models against jailbreak attacks.

  5. Jailbreak Attacks and Defenses Against Large Language Models: A Survey

    cs.CR 2024-07 accept novelty 4.0

    A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.

  6. AI Trust OS -- A Continuous Governance Framework for Autonomous AI Observability and Zero-Trust Compliance in Enterprise Environments

    cs.AI 2026-04 unverdicted novelty 3.0

    AI Trust OS is a proposed always-on operating layer that discovers undocumented AI systems via telemetry and produces continuous zero-trust compliance artifacts for regulations including ISO 42001, EU AI Act, SOC 2, G...

  7. Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

    cs.CR 2024-09 unverdicted novelty 2.0

    Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.