David Mazieres

Geoffrey Ramseyer, Ashish Goel, David Mazieres

In order to scale transaction rates for deployment across the global web, many cryptocurrencies have deployed so-called "Layer-2" networks of private payment channels. An idealized payment network behaves like a Credit Network, a model for transactions across a network of bilateral trust relationships. Credit Networks capture many aspects of traditional currencies as well as new virtual currencies and payment mechanisms. In the traditional credit network model, if an agent defaults, every other node that trusted it is vulnerable to loss. In a cryptocurrency context, trust is manufactured by capital deposits, and thus there arises a natural tradeoff between network liquidity (i.e. the fraction of transactions that succeed) and the cost of capital deposits. In this paper, we introduce constraints that bound the total amount of loss that the rest of the network can suffer if an agent (or a set of agents) were to default - equivalently, how the network changes if agents can support limited solvency guarantees. We show that these constraints preserve the analytical structure of a credit network. Furthermore, we show that aggregate borrowing constraints greatly simplify the network structure and in the payment network context achieve the optimal tradeoff between liquidity and amount of escrowed capital.

Ali Jose Mashtizadeh, Andrea Bittau, David Mazieres et al.

Recent Pwn2Own competitions have demonstrated the continued effectiveness of control hijacking attacks despite deployed countermeasures including stack canaries and ASLR. A powerful defense called Control flow Integrity (CFI) offers a principled approach to preventing such attacks. However, prior CFI implementations use static analysis and must limit protection to remain practical. These limitations have enabled attacks against all known CFI systems, as demonstrated in recent work. This paper presents a cryptographic approach to control flow integrity (CCFI) that is both fine-grain and practical: using message authentication codes (MAC) to protect control flow elements such as return addresses, function pointers, and vtable pointers. MACs on these elements prevent even powerful attackers with random read/write access to memory from tampering with program control flow. We implemented CCFI in Clang/LLVM, taking advantage of recently available cryptographic CPU instructions. We evaluate our system on several large software packages (including nginx, Apache and memcache) as well as all their dependencies. The cost of protection ranges from a 3-18% decrease in request rate.