Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
InProceedings of the 58th Annual Meeting of the Associa- tion for Computational Linguistics (ACL)
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
TIDAL recovers temporal phase signals from LLM-derived semantics of provisioning metadata to enable complementary CVD placement, reducing overload frequency by 79.1% on production traces.
A mega-cluster-free author-identity map for 5.87B git commits folds 106.8M raw strings into 62.7M canonical identities, validated jointly for splitting and clumping errors.
FLARE-AI is an open-source system that standardizes and routes AI flaw reports across developers, coordinators, and registries using conditional logic for triage.
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
SelPE introduces a selection-guided progressive evolution method for private structured text synthesis that decouples abstraction from schema realization and claims better validity and utility under tight DP budgets in low-data settings.
SemStruct models tables as heterogeneous graphs with GNNs on frozen PLM embeddings to incorporate row co-occurrences for schema matching and reports SOTA results on Valentine and SOTAB-SM benchmarks.
Sparsity-guided distillation enables replacing attention layers in ViTs with simpler sequential modules, with sparser layers showing smaller performance drops.
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
A literature survey that categorizes high-level abstract concept image classification tasks in CV into semantic clusters and identifies persistent challenges and opportunities for hybrid AI approaches.
citing papers explorer
-
Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
Malicious LLM API routers actively perform payload injection and secret exfiltration, with 9 of 428 tested routers showing malicious behavior and further poisoning risks from leaked credentials.
-
TIDAL: Recovering Temporal Phase for Cloud Block Storage Placement from LLM-Derived Semantics
TIDAL recovers temporal phase signals from LLM-derived semantics of provisioning metadata to enable complementary CVD placement, reducing overload frequency by 79.1% on production traces.
-
A Global Author-Identity Map for the World of Code:62.7M Developer Identities from 106.8M Author Strings over 5.87B Commits
A mega-cluster-free author-identity map for 5.87B git commits folds 106.8M raw strings into 62.7M canonical identities, validated jointly for splitting and clumping errors.
-
FLARE-AI: Flaw Reporting for AI
FLARE-AI is an open-source system that standardizes and routes AI flaw reports across developers, coordinators, and registries using conditional logic for triage.
-
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation
Byte-level simulations show subword tokenization improves LLM training mainly via increased throughput and boundary priors.
-
SelPE: Progressive Selection for Private Structured Text Synthesis
SelPE introduces a selection-guided progressive evolution method for private structured text synthesis that decouples abstraction from schema realization and claims better validity and utility under tight DP budgets in low-data settings.
-
SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching
SemStruct models tables as heterogeneous graphs with GNNs on frozen PLM embeddings to incorporate row co-occurrences for schema matching and reports SOTA results on Valentine and SOTAB-SM benchmarks.
-
From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
Sparsity-guided distillation enables replacing attention layers in ViTs with simpler sequential modules, with sparser layers showing smaller performance drops.
-
100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories
A literature survey that categorizes high-level abstract concept image classification tasks in CV into semantic clusters and identifies persistent challenges and opportunities for hybrid AI approaches.